© 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. 32-TRANSCODER-HP
    4. 41572
    Prev
    Next
    INDEX
    Explanations

    incidents and errors

    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
    ins
    -0.29
    è¡Į
    -0.28
     ins
    -0.28
    åįļ
    -0.27
     subs
    -0.27
    oks
    -0.27
    acks
    -0.25
    dense
    -0.25
    uls
    -0.25
    rical
    -0.24
    POSITIVE LOGITS
     Searches
    0.30
     free
    0.30
     recognition
    0.28
     Recognition
    0.28
     determination
    0.28
    çĮİ
    0.28
    hunt
    0.27
    FREE
    0.27
    PIN
    0.26
     control
    0.26
    Activations Density 0.009%

    No Known Activations