© 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. 27054
    Prev
    Next
    INDEX
    Explanations

    venturing on journeys

    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
    åŀ¸
    -0.09
    è¦ģç´§
    -0.09
     Marino
    -0.09
    éĵĽ
    -0.08
    çªģåĩºéĹ®é¢ĺ
    -0.08
    éļıæīĭ
    -0.08
    æĥij
    -0.08
    çĨ¨
    -0.08
    è¾İ
    -0.08
    çķ´
    -0.08
    POSITIVE LOGITS
    å²Ľ
    0.09
    åİ»çľĭçľĭ
    0.09
    å°Ŀè¯ķ
    0.09
    liner
    0.08
    daq
    0.08
    elay
    0.08
    æīĵéĢłæĪIJ
    0.08
    åºľ
    0.08
    大èĥĨ
    0.08
    -alone
    0.08
    Activations Density 0.008%

    No Known Activations