© 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. 107080
    Prev
    Next
    INDEX
    Explanations

    Code and technical content

    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
    ;break
    -0.25
    &t
    -0.25
    é¦Ļ
    -0.25
    æľĪä¸Ń
    -0.25
    _RESOLUTION
    -0.25
    Ĩµ
    -0.25
    kart
    -0.24
    icers
    -0.23
    ktop
    -0.23
     grips
    -0.23
    POSITIVE LOGITS
    以ä¸Ĭ
    0.30
    åĪ¨
    0.29
    以ä¸ĬçļĦ
    0.27
     partially
    0.27
     additional
    0.26
    å¿ħè¦ģçļĦ
    0.26
    æģ¶
    0.26
    顽
    0.26
    Additional
    0.25
    å¤ĸæı´
    0.25
    Activations Density 1.002%

    No Known Activations