© 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. 39927
    Prev
    Next
    INDEX
    Explanations

    Intuit or .se email addresses

    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
    寥
    -0.08
    è§ĤçĤ¹
    -0.08
    大家åĪĨ享
    -0.08
    çIJIJ
    -0.08
    åłĨæĶ¾
    -0.08
    趸
    -0.08
    æŶéĹ´æ®µ
    -0.08
    uces
    -0.08
    atur
    -0.08
    轻微
    -0.08
    POSITIVE LOGITS
     outr
    0.09
    laus
    0.09
     нового
    0.09
    ä¸Ģéģĵ
    0.09
    geh
    0.09
     меÑĢ
    0.09
    sher
    0.08
    ullah
    0.08
    åIJ¦
    0.08
    tober
    0.08
    Activations Density 0.003%

    No Known Activations