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. 7-TRANSCODER-HP
    4. 98035
    Prev
    Next
    INDEX
    Explanations

    age

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_7.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.7.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oot
    -0.29
    omy
    -0.25
    纯æ´ģ
    -0.25
    åīįéĢĶ
    -0.24
    -corner
    -0.24
     commencement
    -0.24
     mys
    -0.24
    èįīæ¡Ī
    -0.24
    éģ¿
    -0.23
    æĦŁæĥħ
    -0.23
    POSITIVE LOGITS
    å§Ķå±Ī
    0.28
     Herman
    0.28
    urniture
    0.25
     Stoke
    0.25
     visitor
    0.25
     stools
    0.24
    Slides
    0.24
    çīĽ
    0.24
     Fir
    0.23
    èĩªæĿ¥
    0.23
    Activations Density 0.003%

    No Known Activations