© 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. 31264
    Prev
    Next
    INDEX
    Explanations

    article or code source

    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
    åĬŁè¯¾
    -0.09
    èĭij
    -0.09
    amp
    -0.09
    æľįä»İ
    -0.08
    oped
    -0.08
    amar
    -0.08
    éĩİå¤ĸ
    -0.08
     wyÅĤÄħcznie
    -0.08
    æĿijèIJ½
    -0.08
    æľªæĿ¥åıijå±ķ
    -0.08
    POSITIVE LOGITS
     rtl
    0.09
    NotSupportedException
    0.09
    åIJ®
    0.09
    isors
    0.08
    /*@
    0.08
    /includes
    0.08
    INAL
    0.08
    hor
    0.08
    suit
    0.08
    aget
    0.08
    Activations Density 0.254%

    No Known Activations