© 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. 48045
    Prev
    Next
    INDEX
    Explanations

    salary and compensation details

    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
    zych
    -0.08
    æī¹åıijå¸Ĥåľº
    -0.08
    ga
    -0.08
    åŁŃ
    -0.08
    ime
    -0.08
    èѦ
    -0.08
    wave
    -0.08
    æĺĤ
    -0.07
    æ¶Į
    -0.07
    æİł
    -0.07
    POSITIVE LOGITS
    åīįæĻ¯
    0.10
    ä¼ijæģ¯
    0.09
    åı¯è¾¾
    0.09
    å¼Ģä¸ļ
    0.09
    èĸªéħ¬
    0.09
    /gallery
    0.09
    å¾ħéģĩ
    0.09
     Foley
    0.09
    CellStyle
    0.09
    æĪIJçĨŁ
    0.09
    Activations Density 0.044%

    No Known Activations