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. 23-TRANSCODER-HP
    4. 7484
    Prev
    Next
    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jahres
    -0.26
     sÃłng
    -0.25
    'y
    -0.25
    å®®
    -0.24
    ðŁijĩ
    -0.23
    liches
    -0.23
    à¤ŀ
    -0.23
     fucking
    -0.23
    liche
    -0.23
    æĮĿ
    -0.23
    POSITIVE LOGITS
     Malone
    0.28
    满
    0.27
    .Empty
    0.25
    holds
    0.24
    æ³¥
    0.24
    赤
    0.23
    éļ¶
    0.23
     wrapping
    0.23
    使
    0.23
    .statusText
    0.23
    Activations Density 0.018%

    No Known Activations