© 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. 30272
    Prev
    Next
    INDEX
    Explanations

    GT Masters, GT Racing, GTAV

    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
    lesh
    -0.09
    oji
    -0.09
    ooks
    -0.09
    lessly
    -0.09
    ho
    -0.09
    der
    -0.08
    anth
    -0.08
    Abb
    -0.08
    iy
    -0.08
    orth
    -0.08
    POSITIVE LOGITS
    ALSE
    0.11
    çĦ¶æĺ¯
    0.10
    inel
    0.09
    ãĤįãģĨ
    0.09
    ente
    0.09
    çݩ家们
    0.09
    æµģæĦŁ
    0.09
    çľģåĨħ
    0.09
    æīĭå¥Ĺ
    0.09
    ¹
    0.09
    Activations Density 0.023%

    No Known Activations