© 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. 63600
    Prev
    Next
    INDEX
    Explanations

    organization or group named

    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
    åħ¶æīĢ
    -0.10
    éĤ£ä¸ĢåĪ»
    -0.10
    åħ¶
    -0.10
    è¿Ļä¸ĢåĪ»
    -0.10
    å¤ĸå©Ĩ
    -0.09
    ä¸Ģç§Ĵ
    -0.09
    éĽĨåĽ¢æĹĹä¸ĭ
    -0.08
     millennia
    -0.08
    åľºä¸Ĭ
    -0.08
    大家
    -0.08
    POSITIVE LOGITS
    vos
    0.11
    èŀį
    0.10
    è¿ĺåı¯
    0.09
    bens
    0.09
    paid
    0.09
    讣
    0.08
    iliar
    0.08
    .Accessible
    0.08
    åĪijäºĭæ¡Ī件
    0.08
    è°Ł
    0.08
    Activations Density 0.010%

    No Known Activations