© 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. 40342
    Prev
    Next
    INDEX
    Explanations

    random 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
     waive
    -0.30
     come
    -0.28
    oref
    -0.27
     aio
    -0.27
     tenant
    -0.27
     threaten
    -0.26
    身
    -0.26
    atch
    -0.26
     coordinate
    -0.26
    away
    -0.26
    POSITIVE LOGITS
     Emerald
    0.32
    semblies
    0.27
     irres
    0.26
    enerative
    0.25
    iffies
    0.25
    Berry
    0.25
    chner
    0.25
    éĤ£æŶ
    0.24
    ccak
    0.24
    ients
    0.24
    Activations Density 28.932%

    No Known Activations