© 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. 23970
    Prev
    Next
    INDEX
    Explanations

    assigned, assignment

    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
    è§ĦèĮĥ
    -0.08
    JKLM
    -0.08
    æĺ§
    -0.08
    仿
    -0.08
    MESS
    -0.08
    æĬ±çĿĢ
    -0.08
    .bundle
    -0.08
     Mess
    -0.08
    posix
    -0.08
    åijĬè¯ī
    -0.08
    POSITIVE LOGITS
    åĪĨéħį
    0.16
     assigned
    0.13
    æijĬ
    0.12
    è¿IJæ°Ķ
    0.12
     asign
    0.12
    幸è¿IJ
    0.12
    çļĦåij½è¿IJ
    0.12
    æĬ½
    0.12
    assigned
    0.12
    çŃ¾
    0.12
    Activations Density 0.093%

    No Known Activations