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. 46430
    Prev
    Next
    INDEX
    Explanations

    wanted

    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
    å®ŀä½ĵ
    -0.28
     playable
    -0.27
    los
    -0.26
    彩
    -0.24
    /gallery
    -0.24
     improvised
    -0.24
    icap
    -0.24
     оÑĤлиÑĩ
    -0.24
    itarian
    -0.24
     pads
    -0.24
    POSITIVE LOGITS
    _USAGE
    0.30
     Surround
    0.28
    meg
    0.27
     triang
    0.27
    bell
    0.25
     Haram
    0.25
    Meg
    0.24
    龸æ°Ķ
    0.24
    åĨĪ
    0.24
     Meg
    0.24
    Activations Density 0.802%

    No Known Activations