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. 7-TRANSCODER-HP
    4. 92945
    Prev
    Next
    INDEX
    Explanations

    Pis/Pisa

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_7.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.7.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĦ¦
    -0.27
    åijĬè¯īä½ł
    -0.27
     Hogan
    -0.26
    ignal
    -0.25
     declar
    -0.25
    åijĬè¯ī
    -0.25
    ç²¾å¿ĥ
    -0.25
    аÑģÑĤ
    -0.25
    ash
    -0.25
     tats
    -0.25
    POSITIVE LOGITS
    oby
    0.25
    衽
    0.25
     pris
    0.25
     onion
    0.25
     PRES
    0.24
    scription
    0.23
    aData
    0.23
    æĭĽåĭŁ
    0.23
    plash
    0.23
    onym
    0.23
    Activations Density 0.002%

    No Known Activations