© 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. 54152
    Prev
    Next
    INDEX
    Explanations

    guaranteed or assure

    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
    enden
    -0.10
    åģ¶
    -0.10
    å®Ľ
    -0.09
    eeper
    -0.09
     ÑĢол
    -0.09
    URI
    -0.08
    ponent
    -0.08
    å®īåħ¨ä¿Ŀéļľ
    -0.08
    ç½Ķ
    -0.08
    ×ķ×¢
    -0.08
    POSITIVE LOGITS
    æĪij们éĥ½
    0.10
     chá»ĭu
    0.09
    ãģ¡ãĤĩãģĨ
    0.08
    _RF
    0.08
    ç»ĻåĬĽ
    0.08
    pis
    0.08
    ãģĬãģĭ
    0.08
    SQ
    0.08
     Bris
    0.08
    æ¿Ĥ
    0.08
    Activations Density 0.010%

    No Known Activations