© 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. 34948
    Prev
    Next
    INDEX
    Explanations

    original copy, proposition that

    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
    åį±
    -0.09
    1
    -0.09
    æŶåħī
    -0.09
    8
    -0.08
    3
    -0.08
    æĹ¥åĨħ
    -0.08
    6
    -0.08
    æĦīå¿«
    -0.08
    7
    -0.08
    æĵį
    -0.08
    POSITIVE LOGITS
    ãģ£ãģ±
    0.10
    HEN
    0.10
    KHTML
    0.09
    sta
    0.09
    åĵĹ
    0.09
    å½±éĻ¢
    0.09
    à¹Īาà¸ĩ
    0.09
    éĺ´éĺ³
    0.09
    chin
    0.09
    Islamic
    0.09
    Activations Density 0.042%

    No Known Activations