© 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. 22-TRANSCODER-HP
    7. 87648
    Prev
    Next
    INDEX
    Explanations

    online activity, assignments, coding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ael
    -0.24
    尺度
    -0.24
    åıªè§ģ
    -0.24
    _THRESH
    -0.24
    éĶľ
    -0.24
     >>↵↵
    -0.24
    éĺ¿å§¨
    -0.24
    åij¨å²ģ
    -0.23
    quiv
    -0.23
    __',
    -0.23
    POSITIVE LOGITS
    red
    0.28
    åĪĽæĸ°èĥ½åĬĽ
    0.28
    id
    0.27
    \
    0.26
    heads
    0.26
     matters
    0.25
    hp
    0.25
    rug
    0.25
    b
    0.25
    E
    0.24
    Activations Density 0.002%

    No Known Activations