© 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. 55479
    Prev
    Next
    INDEX
    Explanations

    click here

    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
    æĥ³æĥ³
    -0.11
    arat
    -0.09
    çĸ£
    -0.09
    巴士
    -0.09
    bye
    -0.09
    ç½ijä¸Ĭ
    -0.08
    .dispose
    -0.08
    izedName
    -0.08
    /root
    -0.08
     íĻĪíİĺìĿ´ì§Ģ
    -0.08
    POSITIVE LOGITS
    诸
    0.09
    åĬ¨
    0.09
    é²ľ
    0.08
     perman
    0.08
    ç¹ģ
    0.08
    lies
    0.08
    çĹķ
    0.08
     ÑħозÑıй
    0.08
    _fsm
    0.08
    è´¤
    0.07
    Activations Density 0.056%

    No Known Activations