© 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. 22194
    Prev
    Next
    INDEX
    Explanations

    variety of services and topics

    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
    æĬ½åĩº
    -0.09
    æĽ²
    -0.09
    æµģæ°´
    -0.09
     perch
    -0.09
    yme
    -0.08
    hap
    -0.08
    ihn
    -0.08
    kek
    -0.08
     æĽ
    -0.08
    )&&
    -0.08
    POSITIVE LOGITS
    涵çĽĸäºĨ
    0.11
    åħŃ大
    0.10
    å¹¿æ³ĽçļĦ
    0.10
    å¹¿æ³Ľ
    0.09
    诸å¦Ĥ
    0.09
    ä¸ī大
    0.09
    åĽĬ
    0.09
    ä¸ĥ大
    0.09
    å±ħ室
    0.09
    æĭĽçīĮ
    0.09
    Activations Density 0.091%

    No Known Activations