© 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. 20-TRANSCODER-HP
    7. 63477
    Prev
    Next
    INDEX
    Explanations

    technical/scientific/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bourg
    -0.29
    åĮĻ
    -0.27
    acom
    -0.25
    åŃĽ
    -0.25
    è¥Ħ
    -0.25
     DOJ
    -0.25
     IDD
    -0.25
     CommandType
    -0.25
     ()č↵
    -0.25
     OMX
    -0.25
    POSITIVE LOGITS
     cam
    0.27
     term
    0.27
    er
    0.27
     relative
    0.26
    çĽ¸å¯¹
    0.25
     m
    0.25
     shortage
    0.25
     for
    0.25
     therm
    0.25
    zed
    0.24
    Activations Density 16.676%

    No Known Activations