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. 73017
    Prev
    Next
    INDEX
    Explanations

    Sales/business

    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
    éͤ
    -0.28
     Collapse
    -0.27
    collapse
    -0.25
    INGTON
    -0.25
     createdBy
    -0.24
    润
    -0.24
    çļĦç¡®æĺ¯
    -0.24
    é«ĺç´łè´¨
    -0.24
    åįĥ
    -0.23
    ABILITY
    -0.23
    POSITIVE LOGITS
    eyed
    0.30
    eras
    0.29
    spy
    0.28
    yc
    0.26
    azines
    0.25
    icy
    0.25
    бÑĭ
    0.25
    _TA
    0.24
    gettext
    0.24
    yps
    0.24
    Activations Density 0.024%

    No Known Activations