© 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. 3781
    Prev
    Next
    INDEX
    Explanations

    using, for, in, as

    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
    malink
    -0.11
    uter
    -0.09
    èĭ´
    -0.08
    (tol
    -0.08
    tls
    -0.08
    еÑģÑĤв
    -0.08
    unnel
    -0.08
    ogl
    -0.08
    çĿĢä»ĸ
    -0.08
    åĩ«
    -0.08
    POSITIVE LOGITS
    Oops
    0.08
    ledge
    0.08
    æĿ¥è¿Ľè¡Į
    0.08
    hani
    0.07
    åı¯ä»¥éĢīæĭ©
    0.07
    åħļé£İ
    0.07
    nex
    0.07
     Oops
    0.07
    GD
    0.07
     assemblies
    0.07
    Activations Density 0.270%

    No Known Activations