© 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. 1978
    Prev
    Next
    INDEX
    Explanations

    invincible, fearless, unbreakable

    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
    ä¸įå®ī
    -0.09
    ä¸įçĶĺ
    -0.09
    çĥĻ
    -0.09
    达人
    -0.08
    BI
    -0.08
    Spe
    -0.08
    éĶ¦
    -0.08
    çĭŃçªĦ
    -0.08
    æIJģ
    -0.08
    æ¸ħè¿ľ
    -0.08
    POSITIVE LOGITS
    æĹłæķĮ
    0.10
    ä¸įæĢķ
    0.10
    .Inv
    0.10
     Inv
    0.10
    åħįçĸ«
    0.10
     undefeated
    0.10
    _inv
    0.10
     inv
    0.10
     Emanuel
    0.10
     immunity
    0.09
    Activations Density 0.057%

    No Known Activations