© 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. 29960
    Prev
    Next
    INDEX
    Explanations

    shared access among users

    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
    åħ¶å®ĥéĹ®é¢ĺ
    -0.09
    оÑī
    -0.09
    lfw
    -0.09
    æĢł
    -0.09
     иÑģÑĤоÑĩник
    -0.09
    åIJij社ä¼ļ
    -0.09
    makt
    -0.09
    ssel
    -0.09
    iek
    -0.09
    disposed
    -0.09
    POSITIVE LOGITS
    åħ±äº«
    0.11
    _shared
    0.10
    shared
    0.10
    -shared
    0.10
     shared
    0.09
     pret
    0.09
     Shared
    0.09
    å¤ļ人
    0.09
    åħ±åIJĮ
    0.09
    åħ±å»º
    0.09
    Activations Density 0.130%

    No Known Activations