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. 24052
    Prev
    Next
    INDEX
    Explanations

    school

    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
    alin
    -0.26
    _deps
    -0.26
    éĻĦä»¶
    -0.26
    aina
    -0.26
    ,U
    -0.25
    ervoir
    -0.25
    лин
    -0.24
    rick
    -0.24
     Vent
    -0.24
     Vinci
    -0.24
    POSITIVE LOGITS
    ctal
    0.26
     versa
    0.25
    éĢĤç͍
    0.25
    顺
    0.24
    æŃ¥
    0.24
    .office
    0.24
     нам
    0.24
    éĤ®
    0.24
     /
    0.24
    éĢĤåºĶ
    0.23
    Activations Density 0.005%

    No Known Activations