© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 97401
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    esan
    -0.30
    edb
    -0.28
    andra
    -0.28
     dsp
    -0.26
    äºĶå¹´
    -0.26
    urt
    -0.25
    elage
    -0.25
    第äºĶå±Ĭ
    -0.24
     BTS
    -0.24
    drs
    -0.24
    POSITIVE LOGITS
     incidence
    0.31
     bears
    0.26
    èĤ¯å®ļæĺ¯
    0.25
    修为
    0.25
    INC
    0.25
    umber
    0.25
    oot
    0.24
    inc
    0.24
     bear
    0.24
    表çݰ为
    0.23
    Activations Density 0.009%

    No Known Activations