© 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. 56151
    Prev
    Next
    INDEX
    Explanations

    agon, athon, iron, on, tron

    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
    ëģĶ
    -0.09
    ures
    -0.09
    undef
    -0.09
    ÑĢÑĭв
    -0.09
    mate
    -0.09
    LER
    -0.09
    way
    -0.09
    ye
    -0.09
    游è§Ī
    -0.09
    ele
    -0.08
    POSITIVE LOGITS
    ality
    0.16
    imbus
    0.14
     behalf
    0.13
    naire
    0.12
    shore
    0.12
    nect
    0.12
    岸
    0.11
    UBLE
    0.11
    neau
    0.11
    æĵĴ
    0.11
    Activations Density 0.202%

    No Known Activations