© 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. 39578
    Prev
    Next
    INDEX
    Explanations

    combined with

    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
    vars
    -0.09
    å°±è¿Ļä¹Ī
    -0.09
    ä¸įçĶ±
    -0.08
    å®ŀè·µä¸Ń
    -0.08
    дан
    -0.08
    oo
    -0.08
    lon
    -0.08
    alex
    -0.08
     sl
    -0.08
    å®ŀè·µ
    -0.08
    POSITIVE LOGITS
    åĬłä¸Ĭ
    0.26
    åĨįåĬłä¸Ĭ
    0.25
    åĬłä¹ĭ
    0.21
    ç»ĵåIJĪ
    0.18
     ÑģоÑĩеÑĤ
    0.17
    éħįåIJĪ
    0.16
    éħįä¸Ĭ
    0.16
    ä¼´éļıçĿĢ
    0.15
    æIJŃéħį
    0.14
     combined
    0.14
    Activations Density 0.103%

    No Known Activations