© 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. 24-TRANSCODER-HP
    7. 149823
    Prev
    Next
    INDEX
    Explanations

    today

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éªļ
    -0.26
    -basic
    -0.25
     hại
    -0.25
    ä¹Łå¥½
    -0.25
    cur
    -0.24
    /pol
    -0.24
    éĴ§
    -0.24
    _('
    -0.24
    ä¸Ĭè¯ī
    -0.24
    orne
    -0.23
    POSITIVE LOGITS
    为æŃ¢
    0.33
    ëĤł
    0.30
    's
    0.29
    ÃĥO
    0.28
    ’s
    0.27
    erais
    0.27
     afternoon
    0.27
    份
    0.27
    ä¸ĬåįĪ
    0.27
     evening
    0.26
    Activations Density 1.826%

    No Known Activations