© 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. 56008
    Prev
    Next
    INDEX
    Explanations

    Doctor Who companions and adventures

    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
    æ¯ĶåĪĨ
    -0.10
    åĿª
    -0.10
    ä½ĵèĤ²
    -0.10
    è°¯
    -0.09
    ieber
    -0.09
    _tooltip
    -0.09
    亲æĪļ
    -0.08
     GeliÅŁ
    -0.08
    ä¸į该
    -0.08
    æĺº
    -0.08
    POSITIVE LOGITS
    两åįĥ
    0.09
    æ±¾
    0.08
    常æĢģ
    0.08
     Adventure
    0.08
     Adventures
    0.08
     adventure
    0.08
    åĽŀ头
    0.08
    æµĩ
    0.08
    ä¸īåįĥ
    0.08
    Adventure
    0.08
    Activations Density 0.070%

    No Known Activations