© 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. 62538
    Prev
    Next
    INDEX
    Explanations

    positive numbers and values

    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
    agger
    -0.09
    碰
    -0.08
    夷
    -0.08
    éħ¿éĢł
    -0.08
     dens
    -0.08
    æ³ķåħ°
    -0.08
    unt
    -0.08
    öt
    -0.08
    æ¦ī
    -0.08
    容éĩı
    -0.07
    POSITIVE LOGITS
    æŃ£åĢ¼
    0.14
     positive
    0.13
    positive
    0.13
    negative
    0.12
    è´Ł
    0.12
    .Positive
    0.12
    -positive
    0.11
     negative
    0.11
     Positive
    0.11
    Positive
    0.11
    Activations Density 0.492%

    No Known Activations