© 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. 130753
    Prev
    Next
    INDEX
    Explanations

    Non-English and/or code

    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
    INO
    -0.33
    ino
    -0.28
     yönetici
    -0.25
     mass
    -0.24
     generation
    -0.24
    åĽłç´ł
    -0.23
    éĥ½å¸ĤæĬ¥
    -0.23
    OID
    -0.23
    åħ³èģĶ
    -0.23
    rench
    -0.23
    POSITIVE LOGITS
    werk
    0.33
    åIJĦèĩªçļĦ
    0.30
    åı²
    0.29
    åĽ½æ°ijç»ıæµİ
    0.28
    ãĥ¥ãĥ¼
    0.27
    æ¯ı个人éĥ½
    0.26
    å¾½
    0.26
    oglob
    0.26
    icals
    0.26
    俱
    0.26
    Activations Density 0.009%

    No Known Activations