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. 130052
    Prev
    Next
    INDEX
    Explanations

    of

    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
    plane
    -0.30
    沦
    -0.30
    andan
    -0.27
     reim
    -0.26
    roma
    -0.26
    มà¸Ļ
    -0.26
     Cree
    -0.25
     Li
    -0.25
    losed
    -0.24
    Li
    -0.24
    POSITIVE LOGITS
    å¾Ģå¹´
    0.28
     Balk
    0.28
    Keeper
    0.26
     whip
    0.26
    å̼å¾Ĺ
    0.24
    æĮŀ
    0.24
    strup
    0.24
    ibur
    0.24
    igure
    0.23
    tele
    0.23
    Activations Density 0.001%

    No Known Activations