© 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. 129873
    Prev
    Next
    INDEX
    Explanations

    period

    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
    alth
    -0.29
     mas
    -0.26
    .databind
    -0.25
    rying
    -0.25
    åĪĨ彩
    -0.25
     cross
    -0.25
    endir
    -0.25
    pped
    -0.25
    UsageId
    -0.24
     triple
    -0.24
    POSITIVE LOGITS
    yat
    0.29
    åħĭæĭī
    0.28
    CLS
    0.26
     æĢ
    0.25
    æĺ¾çĦ¶
    0.25
    Over
    0.24
    wap
    0.24
    .transparent
    0.24
    æī
    0.24
    被æīĵ
    0.23
    Activations Density 1.857%

    No Known Activations