© 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. 55848
    Prev
    Next
    INDEX
    Explanations

    brooklyn or borough

    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
    Ľå»º
    -0.09
    ä¹¾åĿ¤
    -0.09
    åݦ
    -0.08
    don
    -0.08
     fortune
    -0.08
    onet
    -0.08
    enger
    -0.08
    ifu
    -0.08
    bourne
    -0.08
    åľ°éĿ¢
    -0.08
    POSITIVE LOGITS
    ../../../
    0.09
    çݯåį«
    0.09
    rapper
    0.09
    ä¸įæ¸ħ
    0.09
    atics
    0.09
    anst
    0.09
    èĭĶ
    0.09
    ῶ
    0.08
    Ñģен
    0.08
    ehler
    0.08
    Activations Density 0.006%

    No Known Activations