© 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. 61753
    Prev
    Next
    INDEX
    Explanations

    old + [noun]

    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
    空åīį
    -0.11
    ä¸ĸçķĮä¸ĬæľĢ
    -0.10
    åĩıå¼±
    -0.09
    ä½ľåĵģåĨħ容
    -0.09
    鼶è·Ŀ离
    -0.09
    _EXTERN
    -0.09
    quine
    -0.09
    çŃ·åŃIJ
    -0.09
    åīįæīĢæľªæľī
    -0.09
    phant
    -0.09
    POSITIVE LOGITS
    -fashioned
    0.15
     old
    0.14
    -old
    0.14
    æŧ
    0.13
     ÑģÑĤаÑĢ
    0.13
    (old
    0.13
    èĢģ
    0.13
    old
    0.13
     OLD
    0.12
    èĪĬ
    0.12
    Activations Density 0.107%

    No Known Activations