© 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. 54679
    Prev
    Next
    INDEX
    Explanations

    solo career or band

    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
    å¤§åľ°
    -0.09
    è¿Ļç¯ĩ
    -0.09
    äºļæ´²
    -0.08
    弧
    -0.08
    alu
    -0.08
    .GetText
    -0.08
    èĬ±éĴ±
    -0.08
     зав
    -0.08
    çķ¢
    -0.07
    çĴĭ
    -0.07
    POSITIVE LOGITS
    oser
    0.11
    åľ¨å®¶
    0.11
    âĦħ
    0.11
    inker
    0.10
    æĪIJç«ĭ
    0.09
    æĬķåħ¥
    0.09
     pseud
    0.09
    inki
    0.09
    OSE
    0.09
    çŃı
    0.09
    Activations Density 0.147%

    No Known Activations