© 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. 32-TRANSCODER-HP
    7. 41203
    Prev
    Next
    INDEX
    Explanations

    code/technical text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĽ¢
    -0.29
    trand
    -0.27
    ç®IJ
    -0.27
    enze
    -0.26
    osaic
    -0.26
    å®ĵ
    -0.26
     genetics
    -0.25
    符
    -0.25
    åĪĽä¼¤
    -0.25
    ph
    -0.25
    POSITIVE LOGITS
    çĬ¯
    0.35
    (ld
    0.28
    adx
    0.27
    ocate
    0.27
    å°ıç¨ĭåºı
    0.26
    éro
    0.25
    æī®æ¼Ķ
    0.25
    ADX
    0.23
    åıijçĶŁ
    0.23
    cox
    0.23
    Activations Density 0.004%

    No Known Activations