© 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. 11350
    Prev
    Next
    INDEX
    Explanations

    reaching a goal or extent

    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
    _intervals
    -0.10
    éĢĿ
    -0.10
    abler
    -0.10
    IBLE
    -0.09
    اء
    -0.09
    iliar
    -0.09
    SETTINGS
    -0.09
    kah
    -0.09
    _BIG
    -0.09
    館
    -0.09
    POSITIVE LOGITS
    ä¸Ģ个æĸ°çļĦ
    0.10
    ä¸Ģä½ĵ
    0.09
    åħ¶æīĢ
    0.09
    æĬķèµĦ人
    0.09
    ç¤ģ
    0.09
    å¾Īé«ĺçļĦ
    0.09
    æīĢè°ĵçļĦ
    0.08
    åĵij
    0.08
     extremes
    0.08
     inverse
    0.08
    Activations Density 0.037%

    No Known Activations