© 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. 39104
    Prev
    Next
    INDEX
    Explanations

    authentic and authentication

    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
    isy
    -0.09
    upon
    -0.08
    flake
    -0.08
    çªģåĩº
    -0.08
    ago
    -0.08
    æĺĤ
    -0.08
    TURE
    -0.08
    isci
    -0.08
    /she
    -0.08
    enen
    -0.08
    POSITIVE LOGITS
    enticate
    0.15
    enticator
    0.14
    entic
    0.13
    enticated
    0.12
    atable
    0.12
    ENTICATION
    0.12
    ENTIC
    0.10
     ë¶Ī구íķĺê³ł
    0.10
    entication
    0.10
    ORIZED
    0.10
    Activations Density 0.023%

    No Known Activations