© 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. 150654
    Prev
    Next
    INDEX
    Explanations

    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
     наÑĩина
    -0.28
    _BEGIN
    -0.28
     Begins
    -0.26
    _begin
    -0.26
     tables
    -0.26
    ç¢Į
    -0.26
     Downs
    -0.25
    .WriteString
    -0.25
    _years
    -0.24
    -years
    -0.24
    POSITIVE LOGITS
    utory
    0.30
    åĪĽæĸ°
    0.27
    functional
    0.27
    å¼ĢæĶ¾
    0.26
     provincial
    0.25
    vert
    0.25
    对å¤ĸå¼ĢæĶ¾
    0.25
    åIJ¯çĶ¨
    0.25
     [~,
    0.24
    æŀ¢
    0.24
    Activations Density 0.022%

    No Known Activations