© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 24-TRANSCODER-HP
    7. 149879
    Prev
    Next
    INDEX
    Explanations

    military branches

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å®ĺåı¸
    -0.35
    jes
    -0.27
    ureau
    -0.27
    brains
    -0.25
     //////////////////////////////////////////////////////////////////////
    -0.25
    corn
    -0.25
    éĥ¨å§Ķ
    -0.25
    escal
    -0.25
    -appointed
    -0.24
    .Strings
    -0.24
    POSITIVE LOGITS
     sol
    0.27
     reflective
    0.26
    ovel
    0.26
    è¿ĩ
    0.26
    ê±°ëŀĺ
    0.25
    åIJĮå¿Ĺ
    0.24
     mirror
    0.24
     Field
    0.24
    çĪ±ä½ł
    0.24
     sil
    0.24
    Activations Density 0.098%

    No Known Activations