© 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. 11242
    Prev
    Next
    INDEX
    Explanations

    overnight shipping or fast

    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
    fully
    -0.12
    ëĭ¤ê°Ģ
    -0.09
    fulness
    -0.09
    odem
    -0.09
    бо
    -0.09
    iton
    -0.08
    ocrats
    -0.08
    storms
    -0.08
    eners
    -0.08
     воÑĤ
    -0.08
    POSITIVE LOGITS
    iates
    0.09
    ä¹ĭä½ľ
    0.09
    lient
    0.09
    åĬŁå¤«
    0.09
    mente
    0.09
    å¸ĤæĶ¿åįı
    0.09
    åľ¨ç¾İåĽ½
    0.09
    aÅĤa
    0.08
    ingt
    0.08
    aneously
    0.08
    Activations Density 0.004%

    No Known Activations