© 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. 53208
    Prev
    Next
    INDEX
    Explanations

    forced to

    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
    wich
    -0.09
    åıijå±ķéĺ¶æ®µ
    -0.09
    _Pin
    -0.09
    ating
    -0.09
    æĻº
    -0.08
    .running
    -0.08
    markup
    -0.08
    Ãłng
    -0.08
    pha
    -0.08
    .Transactional
    -0.08
    POSITIVE LOGITS
    迫使
    0.22
    ä¸įå¾Ĺå·²
    0.18
    è¿«
    0.17
    被迫
    0.16
    强迫
    0.16
    éĢ¼
    0.15
     forced
    0.14
    ä¸įå¾Ĺä¸į
    0.14
     Forced
    0.14
    æĹłå¥Ī
    0.13
    Activations Density 0.060%

    No Known Activations