© 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. 38786
    Prev
    Next
    INDEX
    Explanations

    side, half, rear, camp

    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
    çĽ¸ä¼´
    -0.10
    åĴĮå°ļ
    -0.09
    YPES
    -0.09
    æ¶Ľ
    -0.09
    çĶ¨äºº
    -0.09
    /slick
    -0.09
    èį£
    -0.09
    ýt
    -0.09
    onomy
    -0.08
    èľĴ
    -0.08
    POSITIVE LOGITS
    éĺµèIJ¥
    0.15
    éĺµåľ°
    0.15
    éĺµ
    0.11
    éĻ£
    0.11
    éĺµå®¹
    0.10
    ns
    0.10
    appro
    0.10
    hen
    0.10
    igned
    0.09
    éĺ²çº¿
    0.09
    Activations Density 0.022%

    No Known Activations