© 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. 23223
    Prev
    Next
    INDEX
    Explanations

    free agents, Madagascar, variables

    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
    éĶµ
    -0.09
    shaw
    -0.09
    æľªç»ı
    -0.09
    ickers
    -0.08
    quets
    -0.08
    ä¹Ĵä¹ĵ
    -0.08
    çī¢åĽº
    -0.08
    lover
    -0.08
    .xr
    -0.08
    管å±Ģ
    -0.08
    POSITIVE LOGITS
     Ðijа
    0.10
    ysi
    0.09
    NAS
    0.09
    ãĤĴè¿İ
    0.09
    å¸Ĥåľºä¸Ĭ
    0.09
    æ·¼
    0.09
    ãĤĴè¿İãģĪ
    0.09
    efs
    0.09
    ãģ«åIJijãģijãģ¦
    0.09
    tiny
    0.08
    Activations Density 0.002%

    No Known Activations