© 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. 3107
    Prev
    Next
    INDEX
    Explanations

    iconic objects and figures

    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
    ings
    -0.11
    esse
    -0.10
    è¡·
    -0.09
    åĭĥåĭĥ
    -0.09
    wick
    -0.09
    æĪijçĪ±ä½ł
    -0.09
    agoon
    -0.08
    alin
    -0.08
    edException
    -0.08
    enn
    -0.08
    POSITIVE LOGITS
    人çī©
    0.12
    ponent
    0.11
    thon
    0.10
    举æŃ¢
    0.10
    ä¹ĭä½ľ
    0.10
    inine
    0.10
    culate
    0.10
    nection
    0.10
    çªŁ
    0.09
    lical
    0.09
    Activations Density 0.013%

    No Known Activations