© 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. 30819
    Prev
    Next
    INDEX
    Explanations

    in many/eight/mobile

    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
    onne
    -0.09
    è¾Ł
    -0.08
    ä¸ĥæľĪ
    -0.08
    çŁŃ
    -0.08
    pite
    -0.08
    ä¸Ģå¦Ĥ
    -0.08
    isha
    -0.08
    æıIJæĹ©
    -0.08
    _PACK
    -0.08
    éļĶå£ģ
    -0.08
    POSITIVE LOGITS
    èĭ¥å¹²
    0.19
    å¤ļå°ij
    0.18
    ä¸įå°ijäºİ
    0.15
    è¿Ļä¹Īå¤ļ
    0.14
    äºĨå¤ļå°ij
    0.14
     several
    0.14
     fewer
    0.14
    æĢ»åħ±
    0.14
    èĩ³å°ij
    0.13
    æĹłæķ°
    0.13
    Activations Density 0.471%

    No Known Activations