© 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. 53855
    Prev
    Next
    INDEX
    Explanations

    over and over

    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
    åı·ç§°
    -0.09
    oppel
    -0.09
    æŁ´
    -0.09
     наи
    -0.08
    ftar
    -0.08
    egl
    -0.08
    _ACL
    -0.08
    åħ¬è®¤çļĦ
    -0.08
    ạ
    -0.08
    ä¸ºæľŁ
    -0.08
    POSITIVE LOGITS
    çĽ¥
    0.10
    æľīéĹ®é¢ĺ
    0.10
    ä¹İ
    0.09
    æ¶İ
    0.09
    éģįåıĬ
    0.09
    严
    0.09
    ixon
    0.08
    ãĥ¼ãĤ¹
    0.08
    大éħĴåºĹ
    0.08
    å°Ķ
    0.08
    Activations Density 0.007%

    No Known Activations