© 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. 55296
    Prev
    Next
    INDEX
    Explanations

    articles preceding nouns

    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
    è£
    -0.09
    çĸ¾
    -0.09
    éĵİ
    -0.08
    诨
    -0.08
    ä¸Ģ个éĹ®é¢ĺ
    -0.08
    åĹŁ
    -0.08
    еÑģÑĤ
    -0.08
    Lit
    -0.08
    è¿ĻäºĽä¸ľè¥¿
    -0.08
    orn
    -0.08
    POSITIVE LOGITS
    verts
    0.10
     коÑĤоÑĢого
    0.09
    åĨįåĪ°
    0.09
     otherwise
    0.09
    SizeMode
    0.08
    åIJĪæ³ķæĢ§
    0.08
    нÑĮ
    0.08
    åij½åij¨æľŁ
    0.08
    çıª
    0.08
    è¯ł
    0.08
    Activations Density 0.471%

    No Known Activations