© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 23669
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĽ½ç±į
    -0.30
    åıĺäºĨ
    -0.29
    ritch
    -0.28
    举æŃ¢
    -0.26
    é²Ľ
    -0.25
     Vacation
    -0.24
     collectively
    -0.24
    оваÑĤÑĮ
    -0.24
    åij¨åĪĬ
    -0.24
    ndon
    -0.23
    POSITIVE LOGITS
    é¢Ĩ导å°ıç»Ħ
    0.28
    åı¦
    0.27
     sense
    0.26
     crown
    0.25
     fact
    0.25
    sense
    0.25
    çĿ«
    0.24
    纽
    0.24
     Verm
    0.24
     domina
    0.24
    Activations Density 0.008%

    No Known Activations