© 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. 27224
    Prev
    Next
    INDEX
    Explanations

    comfort zone, range, depth

    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
    软
    -0.10
    åĵį
    -0.10
    ìĬĪ
    -0.10
    æ²īéĩį
    -0.10
    ancode
    -0.10
    éŁ¿
    -0.09
    çħ§
    -0.09
     ÙĪز
    -0.09
    èĪģ
    -0.09
    è¿Ļç¯ĩ
    -0.09
    POSITIVE LOGITS
    TimeZone
    0.09
    clone
    0.08
    @g
    0.08
    [:,:,
    0.08
    ynth
    0.08
    rib
    0.08
    ä¸ĢåIJį
    0.08
    æĪ¿æºIJ
    0.08
    zar
    0.08
    ANNOT
    0.08
    Activations Density 0.005%

    No Known Activations