© 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. 35643
    Prev
    Next
    INDEX
    Explanations

    unlimited use

    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
    cycl
    -0.08
     Gang
    -0.08
    ðŁı»
    -0.08
     пен
    -0.08
    gment
    -0.08
     nab
    -0.08
     ciclo
    -0.07
     lam
    -0.07
     веÑĩеÑĢ
    -0.07
    piece
    -0.07
    POSITIVE LOGITS
    tee
    0.11
    пиÑĤ
    0.10
    orrow
    0.10
    åı¦è¡Į
    0.10
    orde
    0.09
    erta
    0.09
    迹
    0.09
    ä¸įéĻIJ
    0.09
    æķĸ
    0.09
    rale
    0.09
    Activations Density 0.010%

    No Known Activations