© 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. 32474
    Prev
    Next
    INDEX
    Explanations

    automotive industry

    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
    ×ķת
    -0.14
    à¹Ĩ
    -0.10
    èij©
    -0.10
    raries
    -0.10
    iams
    -0.10
    à¸Ĺาà¸ĩ
    -0.09
    eric
    -0.09
    /vendors
    -0.09
    ormsg
    -0.09
    们çļĦ
    -0.09
    POSITIVE LOGITS
    yat
    0.10
    æµģæ°ĵ
    0.10
    yla
    0.10
    åıijè¾¾åĽ½å®¶
    0.09
    yard
    0.09
    çĦ¶æĺ¯
    0.09
    åĹŁ
    0.08
    ä»·æł¼ä¸Ĭ涨
    0.08
    家è£ħ
    0.08
    好åIJ§
    0.08
    Activations Density 0.020%

    No Known Activations