© 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. 17624
    Prev
    Next
    INDEX
    Explanations

    cons and following tokens

    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
    -0.12
    ting
    -0.11
    磧
    -0.09
    воÑĢ
    -0.09
    ettes
    -0.09
    渴
    -0.09
    ÑĩаÑĤ
    -0.09
    eners
    -0.08
    ives
    -0.08
    ropa
    -0.08
    POSITIVE LOGITS
    ignment
    0.11
    ervative
    0.10
    istency
    0.09
    om
    0.09
    istent
    0.09
    æłī
    0.09
    æ´¾
    0.09
    obar
    0.08
    solid
    0.08
    al
    0.08
    Activations Density 0.013%

    No Known Activations