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. 27-TRANSCODER-HP
    4. 1203
    Prev
    Next
    INDEX
    Explanations

    code and configuration

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ılı
    -0.32
    amac
    -0.28
    eric
    -0.27
    roups
    -0.27
    åĽĽåij¨
    -0.26
    ä½Ļå®¶
    -0.26
    idas
    -0.26
    ä¸ĩäºĭ
    -0.25
    su
    -0.25
    SHOP
    -0.24
    POSITIVE LOGITS
    ceed
    0.26
    æ»ĩ
    0.26
     footage
    0.25
    ä¿ĿçķĻ
    0.25
    _bases
    0.25
    è¿ĿèĥĮ
    0.25
    è¿Ŀ
    0.25
     whore
    0.25
    .fromLTRB
    0.24
     Fisheries
    0.24
    Activations Density 0.000%

    No Known Activations