© 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. 49470
    Prev
    Next
    INDEX
    Explanations

    James Mason, ClanLib Team

    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
    èĥª
    -0.10
    å®īæĬļ
    -0.09
    海绵
    -0.09
    oker
    -0.08
    eyer
    -0.08
     prefixed
    -0.08
    åĬłå¤§
    -0.08
     wur
    -0.08
    andard
    -0.08
    å¤Ń
    -0.08
    POSITIVE LOGITS
    atha
    0.10
    yme
    0.09
    opsis
    0.09
    æ¡Į
    0.09
    _Frame
    0.08
     Tata
    0.08
    amin
    0.08
    _DIRS
    0.08
    utr
    0.08
    ULT
    0.08
    Activations Density 0.067%

    No Known Activations