© 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. 50083
    Prev
    Next
    INDEX
    Explanations

    continuation or progress

    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
    æĮŁ
    -0.10
    éĥ½è¯´
    -0.10
    ä¹°åįķ
    -0.09
    éļıä¹ĭ
    -0.09
    ä¸ĢéĹ´
    -0.09
    عد
    -0.09
    æĢģ
    -0.09
    ead
    -0.09
    ç»°
    -0.09
    æľĢåħĪè¿ĽçļĦ
    -0.09
    POSITIVE LOGITS
    ä¸Ķ
    0.09
    unts
    0.09
    orus
    0.09
    è¶Ł
    0.08
    åıijå±ķæĪĺçķ¥
    0.08
    gre
    0.08
    voy
    0.08
    chn
    0.07
    æĭ³
    0.07
    gn
    0.07
    Activations Density 0.007%

    No Known Activations