© 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. 22858
    Prev
    Next
    INDEX
    Explanations

    Cannes Film, avi Video, X code

    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
    /manual
    -0.10
    éĢģåĩº
    -0.09
    ipop
    -0.09
    å®ŀéĻħæĥħåĨµ
    -0.09
    æļ§
    -0.08
     actual
    -0.08
    bsub
    -0.08
     Marvin
    -0.08
    uars
    -0.08
    opers
    -0.08
    POSITIVE LOGITS
    èĤ¥
    0.09
    æĶ¾å¤§
    0.08
    æŃ»è§Ĵ
    0.08
    æ¸ħçĪ½
    0.08
    olia
    0.08
    æ¸ħåĩī
    0.08
     Sonia
    0.08
     Muse
    0.08
    enance
    0.08
    éŀ
    0.08
    Activations Density 0.009%

    No Known Activations