© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38293
    Prev
    Next
    INDEX
    Explanations

    picking up

    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
    ä½İè¿·
    -0.10
    aten
    -0.08
     retrie
    -0.08
    æį¶
    -0.08
    缮åħī
    -0.08
    å°´å°¬
    -0.08
    æľįåĬ¡åijĺ
    -0.08
    éĢ¶
    -0.07
    áŀĨ
    -0.07
     FAC
    -0.07
    POSITIVE LOGITS
    æ»Ķ
    0.09
    .updateDynamic
    0.09
    Animating
    0.09
    IPH
    0.09
     Barnes
    0.09
    udes
    0.09
    -animate
    0.09
    etsk
    0.09
    æĦŁè°¢
    0.09
    ç¶ļãģįãĤĴèªŃãĤĢ
    0.09
    Activations Density 0.013%

    No Known Activations