© 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. 97115
    Prev
    Next
    INDEX
    Explanations

    instructions

    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
    Negative Logits
    è¹ī
    -0.29
    pseudo
    -0.28
    ynch
    -0.27
    è¶³å¤Ł
    -0.27
    oku
    -0.26
    slot
    -0.25
     spyOn
    -0.24
     truly
    -0.24
    amac
    -0.24
    chimp
    -0.24
    POSITIVE LOGITS
    åħ¨å±Ģ
    0.27
     Complexity
    0.26
    Disconnect
    0.24
    REET
    0.23
    身ä½ĵåģ¥åº·
    0.23
    è¡ĮåĪĹ
    0.23
    -fly
    0.23
    å¤įæĿĤ
    0.23
     force
    0.23
    æ¶İ
    0.23
    Activations Density 0.007%

    No Known Activations