© 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. 27-TRANSCODER-HP
    7. 58102
    Prev
    Next
    INDEX
    Explanations

    from

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     zro
    -0.30
    -mm
    -0.28
    orgen
    -0.28
    åľ¨æ¸¸æĪıä¸Ń
    -0.28
    å®ŀ
    -0.26
    åĽ½å®¶æĪĺçķ¥
    -0.26
    .DataBind
    -0.26
    DownList
    -0.25
    -DD
    -0.24
    аниÑİ
    -0.24
    POSITIVE LOGITS
     levels
    0.33
     level
    0.32
     Level
    0.30
    0.30
    ech
    0.29
     approximately
    0.28
     Levels
    0.27
     roughly
    0.27
    à¸Ľà¸£à¸°à¸¡à¸²à¸ĵ
    0.27
    _levels
    0.26
    Activations Density 0.005%

    No Known Activations