© 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. 35109
    Prev
    Next
    INDEX
    Explanations

    future or progress

    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
    å¸ĪçĶŁ
    -0.09
    EFF
    -0.09
     spreading
    -0.08
     spread
    -0.08
    åĺĢ
    -0.08
    æłı
    -0.08
    è¾ħ导åijĺ
    -0.08
    aupt
    -0.08
    æĪIJ为ä¸ĢåIJį
    -0.08
    çĺ¿
    -0.08
    POSITIVE LOGITS
    éĹ®è´£
    0.09
    èIJ¼
    0.08
    éĹºèľľ
    0.08
    åħ¬åĬŀ
    0.08
    åĽŀæĿ¥äºĨ
    0.08
    æĮĤéĴ©
    0.08
    请æķĻ
    0.08
    å±ħ
    0.08
    iku
    0.08
    isa
    0.08
    Activations Density 0.112%

    No Known Activations