© 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. 53510
    Prev
    Next
    INDEX
    Explanations

    successful completion

    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
    обоÑĢ
    -0.09
     Kop
    -0.09
    ç«Ł
    -0.08
     опÑĭ
    -0.08
    rame
    -0.08
    ิà¸ģ
    -0.08
    UpdatedAt
    -0.08
    caff
    -0.08
    _filenames
    -0.08
    以为
    -0.08
    POSITIVE LOGITS
    çŃ·
    0.10
    çŃīåĢĻ
    0.10
    æĪIJåĬŁ
    0.10
    edo
    0.09
    大éħĴåºĹ
    0.09
    鹿
    0.09
    çĶŁæķĪ
    0.09
    _INTR
    0.09
    ä¸ĢåŃĹ
    0.09
    åĪĿæŃ¥
    0.08
    Activations Density 0.045%

    No Known Activations