© 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. 35017
    Prev
    Next
    INDEX
    Explanations

    Read instructions or information

    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
    Enc
    -0.08
    _|
    -0.08
    å¾ģ
    -0.08
    çĻ¾å¼º
    -0.08
     Lowell
    -0.08
    mino
    -0.08
     Walters
    -0.08
    çĨĦ
    -0.07
    apan
    -0.07
    ment
    -0.07
    POSITIVE LOGITS
    ä»Ķ
    0.14
    ä»Ķç»Ĩ
    0.14
     carefully
    0.11
    åħ¨èĥ½
    0.10
    ä¸ĭéĿ¢
    0.10
    ç»Ĩå¿ĥ
    0.10
    两端
    0.10
     Mare
    0.10
    好好
    0.10
    æĺ¯å¾Ī
    0.10
    Activations Density 0.039%

    No Known Activations