© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37632
    Prev
    Next
    INDEX
    Explanations

    preceding threshold words

    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
    -ons
    -0.09
     trÄĥm
    -0.09
    è£Ļ
    -0.09
    oking
    -0.09
    ÑĪив
    -0.09
    bern
    -0.09
    å®ĹæŨ
    -0.09
    åĹĿ
    -0.08
    деÑģÑıÑĤ
    -0.08
    ests
    -0.08
    POSITIVE LOGITS
    Reached
    0.10
    edList
    0.10
    å¾Ĺä½ı
    0.09
    nement
    0.09
    mere
    0.09
    idian
    0.09
    éĺĪ
    0.09
    æѤå¤ĸ
    0.09
    ched
    0.09
    nÃŃ
    0.09
    Activations Density 0.035%

    No Known Activations