© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8337
    Prev
    Next
    INDEX
    Explanations

    settings username or file

    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
    sters
    -0.09
    çĦ¶æĺ¯
    -0.09
    ido
    -0.09
    ä¹İ
    -0.09
    廪
    -0.09
    绶
    -0.09
    uments
    -0.09
     Ñģобой
    -0.08
    alytics
    -0.08
    zilla
    -0.08
    POSITIVE LOGITS
    urv
    0.10
    ched
    0.09
    åĽ½æĥħ
    0.09
    ACHED
    0.09
    ween
    0.08
    tle
    0.08
    ually
    0.08
    ÑĤÑĢи
    0.08
    éŃij
    0.08
    оÑĤ
    0.08
    Activations Density 0.040%

    No Known Activations