© 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. 58776
    Prev
    Next
    INDEX
    Explanations

    NOTICE or ICE

    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
    tern
    -0.11
    èĦį
    -0.09
    ÙĪات
    -0.08
    enco
    -0.08
    IJ
    -0.08
    alc
    -0.08
    otr
    -0.08
    æĭĬ
    -0.08
    aze
    -0.08
    æĹłè¾ľ
    -0.08
    POSITIVE LOGITS
    ably
    0.17
    edly
    0.13
    ìĤ¬íķŃ
    0.12
    ABILITY
    0.11
    ively
    0.10
    -taking
    0.10
    å¸ļ
    0.10
    able
    0.10
    éĻIJãĤĬ
    0.10
    odon
    0.09
    Activations Density 0.021%

    No Known Activations