© 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. 112840
    Prev
    Next
    INDEX
    Explanations

    punctuation and code fragments

    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
    acus
    -0.31
    ä½ĨçĶ±äºİ
    -0.28
    èĪªçº¿
    -0.28
    laps
    -0.28
    ailles
    -0.27
    fin
    -0.26
    arus
    -0.25
     vÃŃde
    -0.25
    Ãłn
    -0.24
     nickel
    -0.24
    POSITIVE LOGITS
    ermen
    0.29
    Sup
    0.28
     Med
    0.26
     ÐľÐ¾Ð¶ÐµÑĤ
    0.26
    redient
    0.25
    اÙĦجز
    0.25
     Pride
    0.24
     Part
    0.24
     Suppose
    0.23
    åŀ«
    0.23
    Activations Density 0.007%

    No Known Activations