© 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. 42438
    Prev
    Next
    INDEX
    Explanations

    -and

    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
     sacrific
    -0.29
     catches
    -0.28
    åĨ·èĹı
    -0.28
    èĸ®
    -0.27
    ceased
    -0.26
     haystack
    -0.26
    ä»ĵ
    -0.26
    lec
    -0.25
    LEC
    -0.25
    ellas
    -0.24
    POSITIVE LOGITS
    游
    0.25
    iphy
    0.25
     sur
    0.25
     driving
    0.24
    ier
    0.24
    ijing
    0.24
    ursor
    0.24
    urer
    0.24
    æĹ¥æ¶Īæģ¯
    0.24
    -t
    0.23
    Activations Density 0.001%

    No Known Activations