© 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. 55467
    Prev
    Next
    INDEX
    Explanations

    isolation and separation

    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
    ardy
    -0.09
     grab
    -0.09
    æ¯ģ
    -0.09
    ellites
    -0.09
    ectl
    -0.09
    註
    -0.09
    ç¬ı
    -0.09
    æ®ĭçķĻ
    -0.08
    åIJĪä½ľåįıè®®
    -0.08
    inges
    -0.08
    POSITIVE LOGITS
    éļĶ离
    0.27
    éļĶ
    0.23
     isol
    0.17
     isolation
    0.17
    åĪĨå¼Ģ
    0.16
     isolate
    0.14
    åĪĨ离
    0.14
     separation
    0.13
    åĪĴåĪĨ
    0.13
     оÑĤдел
    0.13
    Activations Density 0.230%

    No Known Activations