© 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. 50408
    Prev
    Next
    INDEX
    Explanations

    settled, established, or grew up around

    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
    å¤§åĽ½
    -0.10
     Thrones
    -0.09
    İĺìĿ´
    -0.09
    çªľ
    -0.09
    åĬłåĪĨ
    -0.08
    ÑīиÑĤ
    -0.08
    è¡ĮåĬ¨
    -0.08
    รà¸ĵ
    -0.08
    ẫn
    -0.08
    秸
    -0.08
    POSITIVE LOGITS
    /ws
    0.08
    emetery
    0.08
    è¿Ħ
    0.08
    iba
    0.08
    ä¸Ģ缴åĪ°
    0.08
    éĽı
    0.08
    avs
    0.08
    æĹ©æľŁ
    0.08
    KeySpec
    0.08
    (Http
    0.08
    Activations Density 0.264%

    No Known Activations