© 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. 33132
    Prev
    Next
    INDEX
    Explanations

    velocity, speed, acceleration, motion

    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
    为人
    -0.09
    -bs
    -0.09
    åĢĴ
    -0.09
    åħģ
    -0.08
     inversion
    -0.08
    ä¸Ĭä¸ĭ
    -0.08
    tap
    -0.08
    -Ta
    -0.08
    æįº
    -0.07
     h
    -0.07
    POSITIVE LOGITS
    è¿IJåĬ¨
    0.13
    éģĭåĭķ
    0.12
    æĸ¹åIJij
    0.11
    æĢµ
    0.10
    lep
    0.10
     TResult
    0.10
    esse
    0.10
    .diag
    0.10
    rench
    0.09
    æĬµæĬĹ
    0.09
    Activations Density 0.098%

    No Known Activations