© 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. 20-TRANSCODER-HP
    7. 106864
    Prev
    Next
    INDEX
    Explanations

    Giving advice/recommendations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     csrf
    -0.26
    çĽijäºĭ
    -0.26
    alyzed
    -0.26
    沤
    -0.26
    åĨ²
    -0.25
    ãģ¾ãģ¨ãĤģ
    -0.25
    ilter
    -0.25
    جاÙĨ
    -0.24
    USA
    -0.24
    ioned
    -0.24
    POSITIVE LOGITS
    ITAL
    0.27
    OrNull
    0.26
    etr
    0.25
    åĨįå¤ļ
    0.25
     då
    0.25
     inexperienced
    0.24
    Attempts
    0.24
    indo
    0.24
    æŀľ
    0.24
    æĬ¥è®°èĢħ
    0.24
    Activations Density 15.983%

    No Known Activations