© 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. 33119
    Prev
    Next
    INDEX
    Explanations

    requesting information or solutions

    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
    STANCE
    -0.09
    ستاÙĨ
    -0.09
    åIJĬ
    -0.09
    æĪĸå¤ļ
    -0.09
     ведÑĮ
    -0.09
    ç¾İå¾·
    -0.09
    apesh
    -0.09
    äºİæѤ
    -0.09
    åĽłä¸ºä»ĸ们
    -0.09
    åIJ¬è¯´
    -0.09
    POSITIVE LOGITS
    änd
    0.08
    ç½
    0.08
    å®īå®ļ
    0.08
    hind
    0.07
     DIS
    0.07
    DIS
    0.07
     wipe
    0.07
     اÙĦÙħس
    0.07
    anson
    0.07
     indifferent
    0.07
    Activations Density 0.021%

    No Known Activations