© 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. 55636
    Prev
    Next
    INDEX
    Explanations

    time periods or durations

    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
    åįģå¹´åīį
    -0.11
    æѧ
    -0.11
    empo
    -0.11
    为äºĨ让
    -0.10
    åĮĻ
    -0.10
    _dispatcher
    -0.10
    åĩłå¹´åīį
    -0.10
    åĪĨ管
    -0.09
     Timing
    -0.09
    å²IJ
    -0.09
    POSITIVE LOGITS
    缴åĪ°
    0.12
    缴èĩ³
    0.12
    ä¸Ģ缴åĪ°
    0.10
     till
    0.09
    è¿ľç¦»
    0.09
     until
    0.09
    ä¸Ģä¸ĸ
    0.08
    æ¦ķ
    0.08
     cob
    0.08
     Offline
    0.08
    Activations Density 0.039%

    No Known Activations