© 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. 3123
    Prev
    Next
    INDEX
    Explanations

    screening contexts

    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
    rees
    -0.11
    ä¸įçĦ¶
    -0.10
    íĴĪ
    -0.10
    ìį¨
    -0.10
    ðŁı»
    -0.10
    åħħæ²Ľ
    -0.10
    cul
    -0.09
    ities
    -0.09
    /current
    -0.09
    orus
    -0.09
    POSITIVE LOGITS
    SHOT
    0.15
    hots
    0.14
    aroo
    0.11
    writers
    0.11
    lining
    0.11
    ве
    0.10
    ural
    0.10
    artin
    0.10
    urally
    0.10
    atic
    0.10
    Activations Density 0.036%

    No Known Activations