© 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. 63360
    Prev
    Next
    INDEX
    Explanations

    margin size, trading, improved, ally, of

    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
    erness
    -0.10
    º
    -0.09
     prospect
    -0.09
    odos
    -0.09
    Ø´Ùħ
    -0.09
    zent
    -0.09
    META
    -0.09
    ened
    -0.09
    onet
    -0.08
    ãģ¾ãĤĭ
    -0.08
    POSITIVE LOGITS
    åľ°å¸¦
    0.14
    ä¸įæ¸ħ
    0.12
    less
    0.11
    éĻ²
    0.11
    edList
    0.11
    edly
    0.10
    æĢ§çĸ¾çĹħ
    0.10
    ierung
    0.10
    ional
    0.10
    ned
    0.10
    Activations Density 0.018%

    No Known Activations