© 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. 1142
    Prev
    Next
    INDEX
    Explanations

    brethren, boro, ibal, annh

    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
    妾
    -0.08
    ç«
    -0.08
    UGE
    -0.08
    ç¨įç¨į
    -0.08
     for
    -0.08
    çªį
    -0.07
    <ul
    -0.07
    干线
    -0.07
    ç»ıéªĮåĴĮ
    -0.07
     MK
    -0.07
    POSITIVE LOGITS
    _b
    0.22
    _B
    0.21
     б
    0.20
     Ðij
    0.20
    æ¹¾
    0.19
     B
    0.19
    ï¼¢
    0.19
    -b
    0.17
    -B
    0.17
    ï½Ĥ
    0.17
    Activations Density 0.322%

    No Known Activations