© 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. 27909
    Prev
    Next
    INDEX
    Explanations

    ask to send or remind

    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
    osi
    -0.10
    足
    -0.09
    PropertyParams
    -0.09
    oley
    -0.09
    _FRIEND
    -0.08
    ç»ĦæĪIJ
    -0.08
    âĩ©
    -0.08
    ê°IJ
    -0.08
    _EVENTS
    -0.08
    igar
    -0.08
    POSITIVE LOGITS
    å©¿
    0.09
    åįħ
    0.09
    æ¯ĭ
    0.09
    ç»Ļä½ł
    0.09
    åĪĨå±Ģ
    0.08
    çĤĶ
    0.08
    åıĤä¸İåĪ°
    0.08
    代
    0.08
    éĥİ
    0.08
    æŁIJ个
    0.08
    Activations Density 0.211%

    No Known Activations