© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6834
    Prev
    Next
    INDEX
    Explanations

    atur

    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
    OID
    -0.01
    елÑĮ
    -0.01
    ongs
    -0.01
    æ±Łåİ¿
    -0.01
    Barrier
    -0.01
    ongsTo
    -0.01
     kab
    -0.01
    OWL
    -0.01
    _BS
    -0.01
    =~
    -0.01
    POSITIVE LOGITS
    ani
    0.01
    æ¯Ľæ³½ä¸ľ
    0.01
     nap
    0.01
    assis
    0.01
    ijn
    0.01
     pen
    0.01
    åŃº
    0.01
    itespace
    0.01
     Harr
    0.01
    æĺµ
    0.01
    Activations Density 1.832%

    No Known Activations