© 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. 62148
    Prev
    Next
    INDEX
    Explanations

    Proper nouns followed by names or locations

    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
    椽
    -0.09
    æŁıæŀĹ
    -0.09
    è¿Ľè´§
    -0.09
    çĵ¯
    -0.09
    èĪ«
    -0.09
    侪
    -0.08
    çĺģ
    -0.08
    çĶ¨å¾®ä¿¡
    -0.08
    _intensity
    -0.08
    StringEncoding
    -0.08
    POSITIVE LOGITS
    egt
    0.08
    aux
    0.08
    Globals
    0.08
    æ´ŀ
    0.08
    è°IJ
    0.08
     handshake
    0.08
    æľīæīĢ
    0.08
     Ful
    0.07
    .delegate
    0.07
     Justin
    0.07
    Activations Density 0.553%

    No Known Activations