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. 65858
    Prev
    Next
    INDEX
    Explanations

    Insects/biology

    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
    eload
    -0.31
     FLAGS
    -0.29
    ä¸ĵ
    -0.28
    unnable
    -0.27
     CONTR
    -0.26
     contr
    -0.25
    ç½ijæĬķ
    -0.25
    驱åĬ¨
    -0.25
     converse
    -0.25
     contradiction
    -0.25
    POSITIVE LOGITS
    ICC
    0.28
    ç©´
    0.27
    abic
    0.26
    çĶ³è¯·äºº
    0.25
    cı
    0.25
    _ABC
    0.25
    æħµ
    0.24
    ancy
    0.24
    hive
    0.24
    ylan
    0.23
    Activations Density 0.580%

    No Known Activations