© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 30174
    Prev
    Next
    INDEX
    Explanations

    touching or being touched

    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
    åijĽ
    -0.11
    涨
    -0.09
    åĪģ
    -0.09
    çķ¸
    -0.09
    åħķ
    -0.09
    emo
    -0.08
    åĴĶ
    -0.08
     Pil
    -0.08
    æİĴåĪĹ
    -0.08
    ç®Ń
    -0.08
    POSITIVE LOGITS
    ç½®äºİ
    0.12
    æIJģ
    0.10
    æĬļ
    0.09
    ç»´å¥ĩ
    0.09
    æĬļæij¸
    0.09
    æħ°
    0.09
    ç¥Ī祷
    0.09
    _schema
    0.08
    èħĵ
    0.08
    vic
    0.08
    Activations Density 0.021%

    No Known Activations