© 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. 61068
    Prev
    Next
    INDEX
    Explanations

    abstract concepts or technical fields

    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
    ÑĨе
    -0.09
    yon
    -0.09
    INAL
    -0.09
    /grpc
    -0.08
    arih
    -0.08
    .Prot
    -0.08
    èĦĬ
    -0.08
    女人
    -0.08
     pope
    -0.08
    sing
    -0.08
    POSITIVE LOGITS
    åĪĴ
    0.11
    åĬĥ
    0.10
    就好
    0.09
    ä»ģ
    0.09
    æ·ħ
    0.09
    åĪĨæĪIJ
    0.09
    çī¹æĸ¯
    0.09
    æ§Ĭ
    0.08
    åĪĩæĪIJ
    0.08
    èĩ³å°ij
    0.08
    Activations Density 0.011%

    No Known Activations