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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7694
    Prev
    Next
    INDEX
    Explanations

    Generic text passage

    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
    èĥ¶
    -0.27
    éĢĥ
    -0.26
    ammad
    -0.26
    masters
    -0.26
    èĢĮéĿŀ
    -0.25
    oulos
    -0.25
    agem
    -0.25
    anine
    -0.25
    ç¼´
    -0.24
    éŃĶæľ¯
    -0.24
    POSITIVE LOGITS
     next
    0.38
     replicate
    0.37
     reuse
    0.37
     continuation
    0.37
     continue
    0.37
     reproduce
    0.36
    next
    0.35
    延ç»Ń
    0.35
    å¤įåĪ¶
    0.35
    _next
    0.35
    Activations Density 0.062%

    No Known Activations