Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 11-TRANSCODER-HP
    4. 146328
    Prev
    Next
    INDEX
    Explanations

    horizontal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_11.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.11.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aload
    -0.28
     depend
    -0.28
     Threshold
    -0.27
    power
    -0.27
     execut
    -0.26
     execute
    -0.26
    Execute
    -0.26
     executing
    -0.26
     threshold
    -0.25
     executed
    -0.25
    POSITIVE LOGITS
    ",__
    0.25
    èµ°åΰ
    0.25
     auss
    0.25
     McKay
    0.25
    endor
    0.24
    lds
    0.24
     '{$
    0.24
    /npm
    0.24
    ="{!!
    0.24
     Tie
    0.23
    Activations Density 0.035%

    No Known Activations