© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 12106
    Prev
    Next
    INDEX
    Explanations

    SQL Server, Marcel, parcel

    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
    ister
    -0.10
    ath
    -0.09
    yer
    -0.08
    ç¥ļ
    -0.08
    ills
    -0.08
    bars
    -0.08
    brew
    -0.08
    羣æŃ£åģļåĪ°
    -0.08
     веÑĩ
    -0.08
    stand
    -0.08
    POSITIVE LOGITS
    ../../
    0.13
    ../../../
    0.12
    	TokenName
    0.10
    jal
    0.10
    Ìģ
    0.09
     Ñģобой
    0.09
    åĽ«
    0.09
    ETHER
    0.09
    ä¹İ
    0.09
    aic
    0.09
    Activations Density 0.006%

    No Known Activations