© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5196
    Prev
    Next
    INDEX
    Explanations

    take

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ously
    -0.29
    Ïİ
    -0.25
    деÑģÑıÑĤ
    -0.25
    ually
    -0.23
    lot
    -0.23
    .lv
    -0.23
     shaken
    -0.23
    _trim
    -0.23
    ÑĢÑĥÑģ
    -0.22
     Translate
    -0.22
    POSITIVE LOGITS
    entered
    0.25
    aways
    0.24
     Miz
    0.23
    иж
    0.23
    ida
    0.23
    .microsoft
    0.23
    ik
    0.23
    æŃ¥åħ¥
    0.22
    ified
    0.22
    使
    0.22
    Activations Density 2.298%

    No Known Activations