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. 45963
    Prev
    Next
    INDEX
    Explanations

    code

    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
    èĬ¡
    -0.32
    æĹłåģ¿
    -0.30
    ffff
    -0.29
    inz
    -0.28
    reas
    -0.28
    rosso
    -0.27
    cff
    -0.27
    fsp
    -0.26
    åIJĮæĹ¶è¿ĺ
    -0.26
    æłĩéħį
    -0.25
    POSITIVE LOGITS
    erm
    0.26
    ative
    0.26
    ä¼ijæģ¯
    0.26
     accepted
    0.25
     Hugo
    0.25
    ä¸ĵä¸ļ
    0.24
     Votes
    0.24
     agon
    0.24
    ativo
    0.24
    vely
    0.23
    Activations Density 0.017%

    No Known Activations