© 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. 6513
    Prev
    Next
    INDEX
    Explanations

    preparation instructions

    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
    ÑģÑĤвÑĥ
    -0.09
    èĢĮ导èĩ´
    -0.09
    太åŃIJ
    -0.09
    衾
    -0.09
    æ©Ħæ¦Ħ
    -0.09
    æĻ¦
    -0.09
    èijĨ
    -0.08
    æĿ¼
    -0.08
    ç´łæĿIJ
    -0.08
    æģ¯
    -0.08
    POSITIVE LOGITS
    çĤ¯
    0.08
     pieces
    0.08
    prefer
    0.08
    usz
    0.08
    _partition
    0.08
    å±ij
    0.08
    åĪĨ红
    0.08
    æŃ¤äºº
    0.07
    åĪĩæĪIJ
    0.07
    dbg
    0.07
    Activations Density 0.002%

    No Known Activations