© 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. 56089
    Prev
    Next
    INDEX
    Explanations

    let me

    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
    å
    -0.10
    çĦī
    -0.10
    åĿŀ
    -0.09
    åŀĴ
    -0.09
    è¿Ħ
    -0.09
    å¹¢
    -0.09
    è¦ģåıĬæŶ
    -0.08
    诸å¦Ĥ
    -0.08
    æĪijåĸľæ¬¢
    -0.08
    ATAR
    -0.08
    POSITIVE LOGITS
    åIJ¬åIJ¬
    0.11
    çľĭçľĭ
    0.10
    umo
    0.09
    æĥ³æĥ³
    0.09
    ãģĦãģĨ
    0.09
    çľĭä¸Ģä¸ĭ
    0.09
    ÑĩиÑģлен
    0.09
    ÙĦÙĪÙĨ
    0.08
    形象
    0.08
    -floating
    0.08
    Activations Density 0.022%

    No Known Activations