© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10402
    Prev
    Next
    INDEX
    Explanations

    registration process

    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
    onest
    -0.10
    icontrol
    -0.09
    ilater
    -0.08
    ÑĢÑĥг
    -0.08
    ÙĦاØŃ
    -0.08
    ottom
    -0.08
     heirs
    -0.08
    yte
    -0.08
    é»ĺå¥ij
    -0.08
    uess
    -0.08
    POSITIVE LOGITS
    æĬ¥åIJį
    0.19
    åıĤåĬł
    0.14
    åıĤèµĽ
    0.12
    åıĤä¼ļ
    0.12
    åıĥåĬł
    0.12
    ç»ĦåĽ¢
    0.10
    è´¹çĶ¨
    0.10
    ç¼´è´¹
    0.10
    éĶIJ
    0.10
    ä½ı宿
    0.10
    Activations Density 0.071%

    No Known Activations