© 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. 30267
    Prev
    Next
    INDEX
    Explanations

    cooking

    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
    FTA
    -0.10
    ARB
    -0.09
    аÑĢа
    -0.09
    书æ³ķ家
    -0.08
    iband
    -0.08
    壮
    -0.08
    æıŃ
    -0.08
    ần
    -0.08
    alto
    -0.08
    æŃ£è§Ħ
    -0.08
    POSITIVE LOGITS
    åģļé¥Ń
    0.12
    å½ķ
    0.11
    èĸ°
    0.10
    isas
    0.10
    Insn
    0.09
    æ²½
    0.09
    çĥ¹
    0.09
    è¶ħé¢Ŀ
    0.09
    çħ®
    0.09
    åľ¨å®¶éĩĮ
    0.09
    Activations Density 0.017%

    No Known Activations