© 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. 62801
    Prev
    Next
    INDEX
    Explanations

    pickup trucks

    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
    eka
    -0.09
    ear
    -0.09
    æŀ¢
    -0.08
    å·¥ç¨ĭæľºæ¢°
    -0.08
    ly
    -0.08
    ically
    -0.08
    /example
    -0.08
    idable
    -0.08
    æ¡ĮåŃIJ
    -0.08
    ew
    -0.08
    POSITIVE LOGITS
    gon
    0.10
     Gener
    0.09
     setAddress
    0.09
    gage
    0.09
    ilon
    0.09
    è¾Ĥ
    0.09
     взÑıÑĤÑĮ
    0.08
    obao
    0.08
     Ars
    0.08
    å½ĺ
    0.08
    Activations Density 0.008%

    No Known Activations