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. 24320
    Prev
    Next
    INDEX
    Explanations

    technical documents

    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
    æ²Ļ
    -0.29
    ForResource
    -0.29
    oter
    -0.28
     coc
    -0.26
    MO
    -0.25
     Buddha
    -0.25
    enn
    -0.25
     MO
    -0.25
     Mo
    -0.25
    abay
    -0.25
    POSITIVE LOGITS
    AFP
    0.27
    ä½ķæĹ¶
    0.26
    è·³åĩº
    0.24
    ä»Ĭ
    0.24
    è¢Ĥ
    0.24
    xp
    0.24
    èĩªä»İ
    0.23
    溴
    0.23
     sill
    0.23
    æĺ¯ä»İ
    0.23
    Activations Density 0.001%

    No Known Activations