© 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. 32-TRANSCODER-HP
    7. 42746
    Prev
    Next
    INDEX
    Explanations

    T

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fluent
    -0.26
    æ¸İ
    -0.26
    uft
    -0.25
     Aç
    -0.25
     Couple
    -0.25
    éĹ²
    -0.24
     fluent
    -0.24
    ensions
    -0.24
     interceptor
    -0.24
    ransition
    -0.24
    POSITIVE LOGITS
    DOMNode
    0.27
    对å¤ĸ
    0.25
    Appear
    0.25
    AMS
    0.25
    rier
    0.25
    illo
    0.25
     Farrell
    0.25
    AttributeValue
    0.24
    ysis
    0.24
    æĮ¯åħ´
    0.24
    Activations Density 0.013%

    No Known Activations