© 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. 33958
    Prev
    Next
    INDEX
    Explanations

    Titanic, titanfall, juggernaut, conglomerates, giants

    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
    inka
    -0.09
    大ä¼Ĺ
    -0.09
    ж
    -0.09
    -speaking
    -0.08
    iba
    -0.08
    Ñĩ
    -0.08
    wares
    -0.08
    éĩijå±±
    -0.07
     Alps
    -0.07
    _KP
    -0.07
    POSITIVE LOGITS
    ä¹ĭä½ľ
    0.12
    åľ©
    0.11
    们çļĦ
    0.11
    ä¿©
    0.10
    æīĭä¸ŃçļĦ
    0.10
    ãģ¶ãĤĬ
    0.10
    们éĥ½
    0.10
    åŃ
    0.09
    itat
    0.09
    0.09
    Activations Density 0.023%

    No Known Activations