© 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. 58427
    Prev
    Next
    INDEX
    Explanations

    crescent, Moon, crest, sickle

    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
    cation
    -0.11
    å¾Ĺèµ·
    -0.09
    ition
    -0.08
     pháºŃn
    -0.08
    å®ŀæĥł
    -0.08
    ç»Īç»ĵ
    -0.08
     constexpr
    -0.08
    大家åĪĨ享
    -0.08
    aversal
    -0.08
    iaux
    -0.08
    POSITIVE LOGITS
    ient
    0.10
    stones
    0.10
    é¢Ŀ
    0.09
    оÑĩек
    0.09
    ingly
    0.09
    stone
    0.09
    uide
    0.09
    ive
    0.09
    é¡į
    0.09
    SHOT
    0.09
    Activations Density 0.009%

    No Known Activations