© 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. 54687
    Prev
    Next
    INDEX
    Explanations

    meeting context

    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
    ively
    -0.11
    ities
    -0.10
    auge
    -0.10
    atra
    -0.09
    çķĮçļĦ
    -0.09
    meld
    -0.09
    Ī
    -0.09
    itted
    -0.09
    -0.09
    undi
    -0.09
    POSITIVE LOGITS
    ioned
    0.13
    ç°ª
    0.10
    ached
    0.10
    ropolis
    0.10
    ropolitan
    0.10
    cobra
    0.09
    EDIUM
    0.08
    па
    0.08
    ssql
    0.08
    æĬĽ
    0.08
    Activations Density 0.022%

    No Known Activations