© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 62786
    Prev
    Next
    INDEX
    Explanations

    hortensias

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĢīåĿĢ
    -0.08
    çŁ³æ¦´
    -0.08
    ousy
    -0.08
     Pitch
    -0.08
    plash
    -0.08
    轶
    -0.08
    arsed
    -0.08
    (JSON
    -0.08
    coin
    -0.08
    ners
    -0.08
    POSITIVE LOGITS
    åIJijãģį
    0.10
    éĻĽ
    0.10
    å¤ĩ
    0.09
    Ñģком
    0.09
    wers
    0.09
    osta
    0.08
    _fake
    0.08
    prox
    0.08
    æĵįä½ľ
    0.08
    reveal
    0.08
    Activations Density 0.008%

    No Known Activations