© 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
    2. Qwen3-4B
    3. 35-TRANSCODER-HP
    4. 39978
    Prev
    Next
    INDEX
    Explanations

    Information, News, and Proper Nouns

    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
    bcd
    -0.34
    icos
    -0.30
    lcd
    -0.28
    cdb
    -0.28
    èİĵ
    -0.27
    cdf
    -0.27
    kp
    -0.27
    ró
    -0.27
    bc
    -0.26
    mk
    -0.26
    POSITIVE LOGITS
     Information
    0.30
     Assistant
    0.29
    Category
    0.29
    Selection
    0.29
     Terms
    0.29
    Version
    0.28
     Sight
    0.28
    Account
    0.28
     Incident
    0.28
     State
    0.28
    Activations Density 64.756%

    No Known Activations