© 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. 18339
    Prev
    Next
    INDEX
    Explanations

    ritualistic behaviors

    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
    aint
    -0.10
    аÑİÑĤÑģÑı
    -0.09
    침
    -0.09
    -eyed
    -0.09
    ëģĶ
    -0.09
    owing
    -0.09
    éĻħ
    -0.08
    åįıä¼ļä¼ļéķ¿
    -0.08
    .au
    -0.08
    ãģĩ
    -0.08
    POSITIVE LOGITS
    istic
    0.20
    istically
    0.12
    æĢ§å¼º
    0.12
    ISTIC
    0.10
    ties
    0.10
    urally
    0.10
    ists
    0.09
    ÑīÑĥ
    0.09
    çļĦãģ«
    0.09
    è§Ħç¨ĭ
    0.09
    Activations Density 0.004%

    No Known Activations