© 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. 39550
    Prev
    Next
    INDEX
    Explanations

    signed for

    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
    åĽ½å®¶éĺŁ
    -0.10
    /moment
    -0.10
    å¹ħ度
    -0.09
    èıĸ
    -0.08
    横
    -0.08
    çļĦä¼Łå¤§
    -0.08
    å¥ł
    -0.08
    é¥Ń
    -0.08
     Widow
    -0.08
    /reset
    -0.08
    POSITIVE LOGITS
    è¡¡
    0.10
    tern
    0.10
     Goodman
    0.10
    çŁ¥
    0.09
    çĤ®
    0.09
    unders
    0.09
    客è¿IJ
    0.09
    ndern
    0.09
    买车
    0.09
    èĭ¦èĭ¦
    0.08
    Activations Density 0.329%

    No Known Activations