© 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. 4784
    Prev
    Next
    INDEX
    Explanations

    University and technology education

    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
    çı°
    -0.09
    çĽ²
    -0.08
    .Automation
    -0.08
    _maker
    -0.08
     Essence
    -0.08
    ä¸Ģ大
    -0.08
     frem
    -0.08
    gro
    -0.08
    ä¿¡èµĸ
    -0.08
    大家éĥ½åľ¨
    -0.08
    POSITIVE LOGITS
    ç¾İåѦ
    0.09
    è§Ĥä¼Ĺ
    0.09
    ÑĤÑĥ
    0.09
    é©´
    0.09
    审ç¾İ
    0.09
    åİ¢
    0.09
     lorem
    0.08
    åĻĹ
    0.08
    æħ°
    0.08
    iens
    0.08
    Activations Density 0.550%

    No Known Activations