© 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. 16586
    Prev
    Next
    INDEX
    Explanations

    bond strength or lengths

    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
    Negative Logits
    ãģĦãģĨ
    -0.10
    èĮ«èĮ«
    -0.09
    hood
    -0.08
    ãģĩ
    -0.08
    odus
    -0.08
    itable
    -0.08
    çļ¿
    -0.08
     handful
    -0.08
    endl
    -0.08
     же
    -0.08
    POSITIVE LOGITS
    edList
    0.13
    çĪ·
    0.12
    yla
    0.11
    å¤
    0.11
    holders
    0.10
    sworth
    0.10
    çł´è£Ĥ
    0.10
    æ§Į
    0.10
    æ®ĸ
    0.10
    åĪĩãĤĮ
    0.09
    Activations Density 0.021%

    No Known Activations