© 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. 56344
    Prev
    Next
    INDEX
    Explanations

    cheek / cheeks

    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
    ÙĨب
    -0.10
    imer
    -0.09
     subj
    -0.09
    ----------------------------------------------------------------------
    -0.09
    å¿ĥåºķ
    -0.08
    èį»
    -0.08
    身躯
    -0.08
    çļĦä¸ĢåĪĩ
    -0.08
    rible
    -0.08
    umb
    -0.08
    POSITIVE LOGITS
    bone
    0.15
    bones
    0.14
    otes
    0.10
    eron
    0.10
    aches
    0.10
    าà¸ģ
    0.09
    ened
    0.09
    zelf
    0.09
     UNUSED
    0.09
    outs
    0.08
    Activations Density 0.007%

    No Known Activations