© 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. 56670
    Prev
    Next
    INDEX
    Explanations

    under the name or ID

    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
     ведÑĮ
    -0.09
    odont
    -0.09
    odon
    -0.09
    SCO
    -0.09
    ç»ĵå©ļ
    -0.09
    çĬ¶
    -0.09
    inct
    -0.09
    纳åħ¥
    -0.09
    çĹ£
    -0.08
    Èĺ
    -0.08
    POSITIVE LOGITS
    uche
    0.10
    åĩ¡
    0.09
    åĢ¾åIJ¬
    0.09
    ä»Ģä¹Īåij¢
    0.09
    [arg
    0.08
     gent
    0.08
    orse
    0.08
    upa
    0.08
    åı£å¤´
    0.08
    ockets
    0.08
    Activations Density 0.107%

    No Known Activations