© 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. 150359
    Prev
    Next
    INDEX
    Explanations

    scientific/technical documents

    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
     assumed
    -0.29
     propensity
    -0.28
    istringstream
    -0.28
    建æŀĦ
    -0.27
    éĩįæŀĦ
    -0.27
    åħ±åIJĮä½ĵ
    -0.26
     assumption
    -0.26
    .Flag
    -0.26
    ä¸įç¡®å®ļæĢ§
    -0.26
     commod
    -0.25
    POSITIVE LOGITS
    flamm
    0.26
    naz
    0.26
     chemotherapy
    0.25
    .Receive
    0.25
    uat
    0.25
    ÑĤÑıж
    0.25
    RAD
    0.24
     navigation
    0.24
    æıĦ
    0.24
    ylum
    0.24
    Activations Density 0.908%

    No Known Activations