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. 53687
    Prev
    Next
    INDEX
    Explanations

    Dates and logic

    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
     ['$
    -0.29
    ág
    -0.27
     dissertation
    -0.26
     (("
    -0.25
    inish
    -0.25
    aux
    -0.25
    erno
    -0.24
    é¢Ħç®Ĺ
    -0.24
    abble
    -0.24
    jem
    -0.24
    POSITIVE LOGITS
     oz
    0.27
    åıijéħµ
    0.26
     Rules
    0.25
     uniqu
    0.25
    rules
    0.25
    _rule
    0.25
     rules
    0.24
    ä¹Łåıªæľī
    0.24
    ster
    0.24
     Seasons
    0.24
    Activations Density 0.073%

    No Known Activations