© 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. 62686
    Prev
    Next
    INDEX
    Explanations

    numbers and counts

    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
    饱
    -0.09
    éĥ½èĥ½å¤Ł
    -0.09
     preval
    -0.09
    åĦ¿å¥³
    -0.09
    è¿Ļä¸ĢçĤ¹
    -0.09
    SCR
    -0.09
    ä¸Ģè¶Ł
    -0.09
    æĭ±
    -0.08
    eral
    -0.08
    åĬĽæ°Ķ
    -0.08
    POSITIVE LOGITS
    ificate
    0.10
    åħ¶ä»ĸçļĦ
    0.09
    teenth
    0.09
    æĿ¥èĩª
    0.09
    BN
    0.08
    lement
    0.08
    å¼Ħå¾Ĺ
    0.08
    éĩijåĪļ
    0.08
     BN
    0.08
    _CALC
    0.08
    Activations Density 0.146%

    No Known Activations