© 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. 33644
    Prev
    Next
    INDEX
    Explanations

    King Kong

    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
    åºł
    -0.10
    ever
    -0.09
    ä¸ĭåįĬ
    -0.09
    çŧ
    -0.08
    eras
    -0.08
    èµĩ
    -0.08
    åĵĢ
    -0.08
    regor
    -0.08
    åħĪ天
    -0.08
    åĽ´æ£ĭ
    -0.08
    POSITIVE LOGITS
    igne
    0.09
    æľªå©ļ
    0.09
    omic
    0.09
    å¶Ĥ
    0.08
    åĿ¦
    0.08
    é«ĺåİŁ
    0.08
    è¸ŀ
    0.08
    é«ĺåľ°
    0.08
     Gladiator
    0.08
    IDI
    0.08
    Activations Density 0.004%

    No Known Activations