© 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. 20248
    Prev
    Next
    INDEX
    Explanations

    rebounds and assists

    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
    åij»
    -0.10
    adro
    -0.09
    yan
    -0.09
    pes
    -0.09
    ences
    -0.08
     ir
    -0.08
    æĽ³
    -0.08
    çĶ³ãģĹ
    -0.08
     SMART
    -0.08
     dip
    -0.08
    POSITIVE LOGITS
    ä½Ĩä¸įéĻIJ
    0.09
    Adj
    0.09
     Cox
    0.09
    forg
    0.08
    ĥ
    0.08
    çĩ¥
    0.08
    uchar
    0.08
    ÙĨسÙĬ
    0.08
    级åĪ«çļĦ
    0.08
    以ä¸ĬçļĦ
    0.08
    Activations Density 0.001%

    No Known Activations