© 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. 39757
    Prev
    Next
    INDEX
    Explanations

    St

    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
     stu
    -0.29
     St
    -0.28
    .St
    -0.27
     conservative
    -0.27
     onBind
    -0.26
     Humph
    -0.26
    ecn
    -0.25
    am
    -0.25
    o
    -0.25
     Thornton
    -0.25
    POSITIVE LOGITS
    åıijè§ī
    0.28
    ä¸įåIJĮæĦı
    0.27
    åıĤåĬłä¼ļè®®
    0.27
     Ride
    0.26
    boom
    0.26
    ius
    0.25
    riv
    0.25
    mts
    0.24
    dds
    0.24
    èĭ¦éļ¾
    0.24
    Activations Density 51.820%

    No Known Activations