© 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. 30640
    Prev
    Next
    INDEX
    Explanations

    beta cells

    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
    æı
    -0.10
     feather
    -0.09
    fé
    -0.09
     TAM
    -0.09
    _FE
    -0.09
    æݥ轨
    -0.08
     Boom
    -0.08
    inho
    -0.08
    ç¾½
    -0.08
    æİ¥
    -0.08
    POSITIVE LOGITS
    æľį
    0.10
     trig
    0.09
    çķ¥
    0.09
    åį´æĺ¯
    0.09
    ç¨İæĶ¶
    0.09
    èĥ°
    0.09
    DJ
    0.08
    讶
    0.08
     sui
    0.08
     ober
    0.08
    Activations Density 0.351%

    No Known Activations