© 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. 3683
    Prev
    Next
    INDEX
    Explanations

    copyright comments

    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
    ä»İèĢĮ使
    -0.09
    FLAG
    -0.09
    ç°Ł
    -0.09
    PropertyParams
    -0.08
    åħļåĨħ
    -0.08
    ãģ¨ãģĻãĤĭ
    -0.08
    éľĩæĥĬ
    -0.08
    éĹ®é¢ĺæĺ¯
    -0.08
    uding
    -0.08
    ucid
    -0.08
    POSITIVE LOGITS
    åµ´
    0.11
    å±ŀ
    0.10
    缤纷
    0.09
    ç¨Ķ
    0.09
    å¼±çĤ¹
    0.08
    æijĩ
    0.08
    getAs
    0.08
    abet
    0.08
    çļĦçģµéŃĤ
    0.08
    ell
    0.08
    Activations Density 0.644%

    No Known Activations