© 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. 35-TRANSCODER-HP
    7. 39749
    Prev
    Next
    INDEX
    Explanations

    technical/scientific text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĥħ
    -0.29
    INATION
    -0.28
    ORIZ
    -0.27
    uib
    -0.27
    riage
    -0.25
    climate
    -0.25
    ras
    -0.25
    ação
    -0.25
    rä
    -0.25
    isers
    -0.24
    POSITIVE LOGITS
     superst
    0.28
    eta
    0.24
     Crane
    0.24
    æİı
    0.24
    大èĩ£
    0.24
    ETA
    0.24
     bets
    0.24
    èĢģçĪ·åŃIJ
    0.23
    å¹´åĨħ
    0.23
     subtle
    0.23
    Activations Density 0.007%

    No Known Activations