© 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. 8331
    Prev
    Next
    INDEX
    Explanations

    commas

    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
     Asi
    -0.25
     verbal
    -0.25
    asic
    -0.25
    .har
    -0.25
    inyin
    -0.24
     Vy
    -0.24
    æģ¶å¿ĥ
    -0.23
    UES
    -0.23
     assignment
    -0.23
    uc
    -0.23
    POSITIVE LOGITS
    æĺ¯å¤ļä¹Ī
    0.27
    æĺ¯æľī
    0.26
    è¿Ļä¹Ī说
    0.24
     Exceptions
    0.24
    çĶĵ
    0.24
    posable
    0.24
    çĥĽ
    0.24
    çľĭå¾Ĺ
    0.23
    éķľ
    0.23
    ç¼ļ
    0.23
    Activations Density 0.042%

    No Known Activations