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. 680
    Prev
    Next
    INDEX
    Explanations

    legal text

    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
    week
    -0.30
    éĩıåĮĸ
    -0.28
    çĮľ
    -0.26
    pery
    -0.26
    _pick
    -0.26
    weekly
    -0.25
    ä¸ĩéĩĮ
    -0.25
    æĦıå¢ĥ
    -0.25
    pper
    -0.25
    ä½ĵ系建设
    -0.25
    POSITIVE LOGITS
     contact
    0.27
    è¯Ń
    0.26
    fullname
    0.26
    REW
    0.26
    ä½ij
    0.25
     Gra
    0.25
     Rope
    0.25
    æ¯į
    0.25
     Contact
    0.23
    ycop
    0.23
    Activations Density 0.002%

    No Known Activations