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. 46034
    Prev
    Next
    INDEX
    Explanations

    code context

    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
    cycl
    -0.27
     clo
    -0.27
    ossal
    -0.25
     cycl
    -0.25
    æĪª
    -0.25
     inf
    -0.24
     Citation
    -0.24
    éĹ®ä»ĸ
    -0.24
     ACT
    -0.24
    umba
    -0.24
    POSITIVE LOGITS
    馥
    0.32
    çϏ
    0.28
    iously
    0.27
    .putString
    0.27
    isión
    0.27
     Kidd
    0.26
    éĻŁ
    0.25
    kul
    0.25
    еÑģÑĤÑĮ
    0.25
    avid
    0.24
    Activations Density 0.034%

    No Known Activations