© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36351
    Prev
    Next
    INDEX
    Explanations

    family of affected individuals

    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
    OTH
    -0.10
    ä½Ĩä¹Ł
    -0.08
    æijŃ
    -0.08
    OTT
    -0.08
     Lewis
    -0.08
    ä¸ĵ家ç»Ħ
    -0.08
    oth
    -0.08
    ollo
    -0.08
    è¯Ħ级
    -0.08
    (OP
    -0.08
    POSITIVE LOGITS
    æ¶īæ¡Ī
    0.10
    驹
    0.10
    缺失
    0.10
    åıĹ害人
    0.09
    åIJ
    0.09
    Toolkit
    0.09
    ÃŃsticas
    0.09
     ThÆ°
    0.09
    è°Ĭ
    0.09
     successful
    0.08
    Activations Density 0.223%

    No Known Activations