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. 146457
    Prev
    Next
    INDEX
    Explanations

    deceleration

    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
    ί
    -0.28
    idy
    -0.27
    wide
    -0.26
    èģ
    -0.26
    åĩºå¢ĥ
    -0.26
    aj
    -0.26
    ä¸įåΰ
    -0.26
     annually
    -0.26
     identity
    -0.25
    =i
    -0.25
    POSITIVE LOGITS
    egas
    0.28
    æ¶Ī
    0.28
    spath
    0.27
    ------------------------------
    0.27
    æ¯Ķäºļ
    0.26
    --------------------
    0.26
     relax
    0.25
     Bethlehem
    0.25
    çļĦæĥħ
    0.25
    SPA
    0.24
    Activations Density 0.014%

    No Known Activations