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. 47108
    Prev
    Next
    INDEX
    Explanations

    7 or 8

    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
    èĻļ
    -0.27
    éĤ®è½®
    -0.25
     noises
    -0.25
    lider
    -0.24
    -exclusive
    -0.24
    离
    -0.24
    æľīéĻIJ
    -0.24
    绿èī²éĢļéģĵ
    -0.24
    绾
    -0.24
     venez
    -0.23
    POSITIVE LOGITS
    丫
    0.27
    毫
    0.27
    ertest
    0.27
     Conte
    0.26
    .handlers
    0.26
    OOT
    0.24
    ris
    0.24
    .setCharacter
    0.23
    Inv
    0.23
    quat
    0.23
    Activations Density 0.351%

    No Known Activations