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. 146284
    Prev
    Next
    INDEX
    Explanations

    industrial automation

    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
    oration
    -0.29
    羣åģĩ
    -0.28
    bart
    -0.26
    attro
    -0.26
    arto
    -0.25
    èıł
    -0.25
    )null
    -0.25
    æľºæ¢°
    -0.25
    å½¢æĢģ
    -0.25
    _delegate
    -0.24
    POSITIVE LOGITS
     schedules
    0.27
     music
    0.25
    éĢĢ
    0.25
    aturas
    0.25
    commit
    0.25
    _GT
    0.24
    éŁ³ä¹IJ
    0.24
    over
    0.23
    олж
    0.23
    lé
    0.23
    Activations Density 0.006%

    No Known Activations