© 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. 62700
    Prev
    Next
    INDEX
    Explanations

    color descriptors

    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
    inary
    -0.10
     Medi
    -0.10
     налиÑĩ
    -0.10
    зи
    -0.09
    å§IJ
    -0.09
    å¯Ĩ
    -0.09
    ä¸įæħİ
    -0.08
    æĥ³å¿µ
    -0.08
    urn
    -0.08
     thần
    -0.08
    POSITIVE LOGITS
    castle
    0.09
    çļĦæłĩåĩĨ
    0.08
    oggled
    0.08
    å·²å®ĮæĪIJ
    0.08
    occasion
    0.08
    çħ¤æ°Ķ
    0.08
    é¢Ħå¤ĩ
    0.08
    åĩºäº§
    0.08
    森æŀĹåħ¬åĽŃ
    0.08
    ühl
    0.08
    Activations Density 0.018%

    No Known Activations