© 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. 11576
    Prev
    Next
    INDEX
    Explanations

    email subscription and removal

    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
    éĩijå±±
    -0.11
    è¹´
    -0.10
    Binder
    -0.10
    çŃ¾çº¦
    -0.09
    åĽ½æľī
    -0.09
    æĶ¹è£ħ
    -0.09
    .getOwnProperty
    -0.09
    åĽłä¸ºå®ĥ
    -0.09
    emer
    -0.09
    çľŁç©º
    -0.09
    POSITIVE LOGITS
    太åŃIJ
    0.08
    rovers
    0.08
     bl
    0.08
    主åĬŀ
    0.08
     Dou
    0.08
    å´Ľ
    0.08
    æŀī
    0.07
    ey
    0.07
    é¬
    0.07
    éľĩæĥĬ
    0.07
    Activations Density 0.010%

    No Known Activations