© 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. 17677
    Prev
    Next
    INDEX
    Explanations

    available followed by what

    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
    人å¿ĥ
    -0.10
    ifying
    -0.10
    ified
    -0.10
    olia
    -0.09
    apped
    -0.09
    illos
    -0.09
    æĺĤ
    -0.09
    åĪ«çļĦ
    -0.09
    ographic
    -0.09
    à¹Į
    -0.09
    POSITIVE LOGITS
     sÃłng
    0.12
    -bodied
    0.11
    èIJĿ
    0.09
    åĪº
    0.09
     Platz
    0.09
    éľĩ
    0.08
    ç¿Ķ
    0.08
    çļĦæĥħæĦŁ
    0.08
    _FIX
    0.08
    atable
    0.08
    Activations Density 0.043%

    No Known Activations