© 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. 57858
    Prev
    Next
    INDEX
    Explanations

    life insurance COMPANY

    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
    _tid
    -0.10
    ç¼Ĺ
    -0.10
    eve
    -0.09
    æĹłç¼Ŀ
    -0.09
    线ä¸Ĭ
    -0.09
    _REMOTE
    -0.09
    _wire
    -0.08
    éŸ
    -0.08
    ÑģÑĤÑĭ
    -0.08
    æªIJ
    -0.08
    POSITIVE LOGITS
    /cms
    0.10
    仵
    0.09
     Sims
    0.09
    eya
    0.09
    åĻ¨å®ĺ
    0.08
    æĸ½å±ķ
    0.08
    å®īåįĵ
    0.08
    à¸Ńà¸ĩ
    0.08
    èĥ¸
    0.08
     lÆ°ng
    0.08
    Activations Density 0.052%

    No Known Activations