© 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. 53710
    Prev
    Next
    INDEX
    Explanations

    theft and stolen goods

    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
    åħīå½±
    -0.09
    0
    -0.08
    4
    -0.08
     ÑĢож
    -0.08
    9
    -0.08
    7
    -0.08
    为äºĨ让
    -0.08
    çļĦæĦ¿æľĽ
    -0.08
    3
    -0.08
    èĢ¦
    -0.08
    POSITIVE LOGITS
    èĥ½å¾ĹåĪ°
    0.10
    è¡ĮæĶ¿æī§æ³ķ
    0.10
    ewan
    0.10
     slime
    0.09
    带走
    0.09
     stealing
    0.09
    çªĥ
    0.09
     slim
    0.09
    lush
    0.09
    è®´
    0.09
    Activations Density 0.028%

    No Known Activations