© 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. 11851
    Prev
    Next
    INDEX
    Explanations

    domain suffixes like .com, .de, .uk

    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
    èĺ¸
    -0.10
    串
    -0.10
    ç¦ıçī¹
    -0.08
    bere
    -0.08
    less
    -0.08
    æ»ļæ»ļ
    -0.08
    èĮ´
    -0.08
    egen
    -0.08
    NY
    -0.08
    azzi
    -0.08
    POSITIVE LOGITS
    бÑĥ
    0.09
    MHz
    0.08
    obe
    0.08
    verte
    0.08
    -wide
    0.08
    åĿı
    0.08
     зак
    0.08
    ðŁĴĬ
    0.08
    زاÙĦ
    0.08
    bud
    0.08
    Activations Density 0.069%

    No Known Activations