© 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. 150124
    Prev
    Next
    INDEX
    Explanations

    .

    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
    åŁİåĮº
    -0.32
    -third
    -0.28
    berger
    -0.28
    ä¸ī家
    -0.26
    第ä¸ī个
    -0.26
    inger
    -0.24
    ERING
    -0.24
    venth
    -0.24
    eming
    -0.24
    INGER
    -0.24
    POSITIVE LOGITS
    ä»ĺ款
    0.27
     plates
    0.25
     lot
    0.25
    èѬå¦Ĥ
    0.25
     Radi
    0.25
    ä¸ĭçļĦ
    0.25
     poison
    0.24
    plates
    0.24
    对æĬĹ
    0.24
    enderit
    0.24
    Activations Density 0.105%

    No Known Activations