© 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. 49919
    Prev
    Next
    INDEX
    Explanations

    FoundationDB and foundation stone

    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
    ened
    -0.11
    onomy
    -0.10
    å®ŀå®ŀåľ¨åľ¨
    -0.10
    ocities
    -0.09
    igo
    -0.09
    æľ
    -0.09
    fov
    -0.09
    ingly
    -0.09
    yna
    -0.09
    /ros
    -0.09
    POSITIVE LOGITS
    aries
    0.12
    nement
    0.12
    istas
    0.10
    ary
    0.10
    ally
    0.10
    ned
    0.10
    lor
    0.10
    naires
    0.10
    arity
    0.10
    ãģĦãĤĭ
    0.09
    Activations Density 0.022%

    No Known Activations