© 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. 1547
    Prev
    Next
    INDEX
    Explanations

    forced against will

    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
    طر
    -0.10
    اÙĨÙĬØ©
    -0.09
    abcdef
    -0.09
    åĩºåħ¥
    -0.09
    director
    -0.09
    éľľ
    -0.09
    yte
    -0.08
    forme
    -0.08
    letters
    -0.08
    ëĶĶ
    -0.08
    POSITIVE LOGITS
    ä¸įå¾Ĺä¸į
    0.12
    åľ¨æĦı
    0.12
    åıªå¥½
    0.11
    强迫
    0.10
    强è¡Į
    0.10
    被迫
    0.10
    åĭī强
    0.10
     forced
    0.10
    ä¸įå¾Ĺå·²
    0.10
    æĤ¬å´ĸ
    0.09
    Activations Density 0.051%

    No Known Activations