© 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. 58800
    Prev
    Next
    INDEX
    Explanations

    sled, slew, or SLE

    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
    ity
    -0.10
    cy
    -0.09
    {}",
    -0.08
    çıł
    -0.08
    èĶ¼
    -0.08
    ians
    -0.08
    ative
    -0.08
    iser
    -0.08
    äºŃ
    -0.08
    åĴ¸
    -0.08
    POSITIVE LOGITS
    æ©ĩ
    0.11
    hammer
    0.10
    iness
    0.10
    éģĺ
    0.09
     horny
    0.09
    _chan
    0.09
    SHOT
    0.09
    Į
    0.09
    homes
    0.09
    ewed
    0.09
    Activations Density 0.007%

    No Known Activations