© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22171
    Prev
    Next
    INDEX
    Explanations

    Blu-ray

    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
    çijŁ
    -0.10
    åĿij
    -0.09
    æĹº
    -0.09
    SWG
    -0.09
     Knot
    -0.09
    stral
    -0.08
    ваÑĤ
    -0.08
    eer
    -0.08
    quisite
    -0.08
    æĹıèĩªæ²»
    -0.08
    POSITIVE LOGITS
    èĢģ人家
    0.10
    wich
    0.10
    rey
    0.09
    çĦ¶æĺ¯
    0.09
    itudes
    0.09
    sch
    0.08
    etail
    0.08
    ãĥĥãģ¨
    0.08
    keit
    0.08
    Ùij
    0.08
    Activations Density 0.004%

    No Known Activations