© 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. 7484
    Prev
    Next
    INDEX
    Explanations

    Positive adjectives

    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
    该
    -0.25
    å·®ä¸įå¤ļ
    -0.25
     rigged
    -0.25
    该éĻ¢
    -0.25
    éģĵè·¯
    -0.24
     Vers
    -0.24
    好äºĨ
    -0.24
     término
    -0.24
    åħ±æľī
    -0.23
    markets
    -0.23
    POSITIVE LOGITS
     male
    0.28
     autos
    0.27
     filler
    0.27
     interchange
    0.25
    blade
    0.25
     intro
    0.24
    ore
    0.24
    ãģªãĤĬ
    0.24
     esp
    0.24
    verb
    0.24
    Activations Density 0.136%

    No Known Activations