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. 67526
    Prev
    Next
    INDEX
    Explanations

    technical/scientific texts

    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
    ç»ķ
    -0.27
    rong
    -0.27
    ÑģÑĤе
    -0.27
     Surround
    -0.27
    ego
    -0.26
    remium
    -0.25
    squeeze
    -0.25
    pper
    -0.25
    ","",
    -0.25
    beiten
    -0.25
    POSITIVE LOGITS
    acic
    0.28
    idea
    0.27
    Tax
    0.26
    Ñģан
    0.25
    metro
    0.24
    ntax
    0.24
    è¿Ļå¥Ĺ
    0.24
    åŃĹ
    0.24
    him
    0.24
    ä¸ĵåįĸ
    0.23
    Activations Density 0.012%

    No Known Activations