© 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. 129290
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
    —"
    -0.28
    ends
    -0.26
    æĪijå¿ĥéĩĮ
    -0.26
    Criteria
    -0.26
     dangerously
    -0.25
    窮
    -0.24
    åıĮèħ¿
    -0.24
    void
    -0.24
    self
    -0.23
    -status
    -0.23
    POSITIVE LOGITS
    çŃĸ
    0.31
    ungan
    0.29
    acin
    0.27
     theor
    0.25
    itto
    0.24
    озд
    0.24
    rink
    0.24
    æ¥Ń
    0.24
    /wiki
    0.23
    nation
    0.23
    Activations Density 0.019%

    No Known Activations