© 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. 38979
    Prev
    Next
    INDEX
    Explanations

    hats and caps

    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
    èĦĨ
    -0.10
    uard
    -0.09
    uis
    -0.09
    ä¸Ģä½ĵ
    -0.09
    çĤ¬
    -0.09
    èĨĺ
    -0.09
    çĶŁäº§åĬĽ
    -0.09
    åħħæ²Ľ
    -0.09
    IMO
    -0.08
    åĬ©æīĭ
    -0.08
    POSITIVE LOGITS
    帽
    0.16
    帽åŃIJ
    0.16
     hats
    0.11
    笳
    0.10
     INCLUDED
    0.10
     dome
    0.09
     Hats
    0.09
    å¥ķ
    0.09
     Dome
    0.09
     Hat
    0.09
    Activations Density 0.021%

    No Known Activations