© 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. 17214
    Prev
    Next
    INDEX
    Explanations

    yards, pounds, pitches

    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
    бо
    -0.09
    åĩıéĢŁ
    -0.09
    ero
    -0.09
     chc
    -0.09
    yro
    -0.09
    ç¼´
    -0.09
    CloseOperation
    -0.09
    ellite
    -0.09
    .toBe
    -0.09
    åĽłä¸ºä½ł
    -0.09
    POSITIVE LOGITS
     lab
    0.08
    çļĦçĭ¬çī¹
    0.08
    orsi
    0.08
    æ©Ľ
    0.08
    æĪijçĪ±ä½ł
    0.08
    çļĦæĦŁåıĹ
    0.08
    æĪijå¦Ī
    0.07
    поÑĩ
    0.07
    eward
    0.07
    rc
    0.07
    Activations Density 0.010%

    No Known Activations