© 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. 27503
    Prev
    Next
    INDEX
    Explanations

    years containing 6

    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
    zek
    -0.10
    iction
    -0.10
    inky
    -0.10
    GRAM
    -0.09
    ixon
    -0.09
    istic
    -0.09
    feeds
    -0.09
    ģ
    -0.09
    еÑĢи
    -0.08
    еÑĩ
    -0.08
    POSITIVE LOGITS
    teenth
    0.20
    ties
    0.15
    деÑģÑıÑĤ
    0.14
    ç¿®
    0.12
    th
    0.11
    ষ
    0.11
    ths
    0.11
    æ°ª
    0.10
    teen
    0.10
    ะ
    0.10
    Activations Density 0.546%

    No Known Activations