© 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. 31-TRANSCODER-HP
    7. 19598
    Prev
    Next
    INDEX
    Explanations

    storms and severe weather

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UCK
    -0.33
    orp
    -0.27
    çĢĽ
    -0.26
    naz
    -0.26
     Examination
    -0.26
    èĴIJ
    -0.25
    itian
    -0.25
     Kund
    -0.25
     Spread
    -0.24
     gob
    -0.24
    POSITIVE LOGITS
    åijĬè¯īä½ł
    0.28
     ê²
    0.26
     approached
    0.25
    èݲ
    0.25
    åĮ»çĸĹ
    0.25
    caret
    0.25
     approach
    0.25
    éĨ«çĻĤ
    0.25
    çī¢
    0.24
    çĥŃ
    0.24
    Activations Density 0.726%

    No Known Activations