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. 1199
    Prev
    Next
    INDEX
    Explanations

    legal and medical documents

    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
    ÂŃtion
    -0.28
    +</
    -0.27
    vé
    -0.27
     Kul
    -0.26
    æī¶è´«å·¥ä½ľ
    -0.25
    ANTA
    -0.25
    mant
    -0.24
    duk
    -0.24
    tion
    -0.24
    representation
    -0.24
    POSITIVE LOGITS
    æľ¬æ¡Ī
    0.25
    _visit
    0.25
    s
    0.24
    Prec
    0.24
    aldi
    0.24
     [{"
    0.24
    .isSuccessful
    0.23
    inburgh
    0.23
     rule
    0.23
    ogle
    0.23
    Activations Density 0.038%

    No Known Activations