© 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. 30157
    Prev
    Next
    INDEX
    Explanations

    feeling confident and reassured

    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
    æ¦Ľ
    -0.09
    èĽŀ
    -0.09
     Truth
    -0.08
    phan
    -0.08
    宣
    -0.08
    undry
    -0.08
    lds
    -0.08
    æĢĴ
    -0.08
    filer
    -0.08
    .YesNo
    -0.08
    POSITIVE LOGITS
    å®īå¿ĥ
    0.26
    æĶ¾å¿ĥ
    0.22
    å®īåħ¨æĦŁ
    0.18
    çļĦä¿¡å¿ĥ
    0.14
    åºķæ°Ķ
    0.13
     confidence
    0.13
    èĩªä¿¡
    0.13
    å®ī稳
    0.13
    ä¿¡å¿ĥ
    0.12
    å®īå®ļ
    0.12
    Activations Density 0.075%

    No Known Activations