© 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. 55074
    Prev
    Next
    INDEX
    Explanations

    checkout and git branch workflow

    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
    æ¹ĥ
    -0.10
    ollection
    -0.10
    chaft
    -0.09
    å½±åĵįåĬĽçļĦ
    -0.09
    亮
    -0.09
     Ire
    -0.09
    arning
    -0.09
    æĬ¼ãģĹ
    -0.08
    è°·
    -0.08
    æ£ķ
    -0.08
    POSITIVE LOGITS
    plib
    0.09
    æµ®
    0.09
    åĵĩ
    0.08
    pu
    0.08
    çģµ
    0.08
    æģ
    0.08
    urat
    0.08
    _utilities
    0.08
    éľģ
    0.08
    oogle
    0.08
    Activations Density 0.010%

    No Known Activations