© 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. 31914
    Prev
    Next
    INDEX
    Explanations

    that's

    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
    ä¸Ģå¦ĤæĹ¢å¾Ģ
    -0.10
    ofs
    -0.09
    -0.09
    åħ¼ä»»
    -0.09
    dings
    -0.09
    座
    -0.09
    åģļçļĦäºĭ
    -0.09
    å¤ĩçĶ¨
    -0.09
    lessly
    -0.08
    (Conv
    -0.08
    POSITIVE LOGITS
    线索
    0.10
     Duch
    0.09
     Mud
    0.09
    为ä»Ģä¹Ī
    0.09
    åıijçĶŁäºĨ
    0.09
     happened
    0.09
    éĩįçĤ¹é¢ĨåŁŁ
    0.09
     why
    0.09
    ter
    0.09
    orny
    0.09
    Activations Density 0.026%

    No Known Activations