© 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. 31463
    Prev
    Next
    INDEX
    Explanations

    Alden, Aldridge, Aldrich, Aldershot

    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
    cribe
    -0.10
    luck
    -0.09
    ting
    -0.09
    abilities
    -0.09
    ä¿ĿåĪ©
    -0.09
    TING
    -0.09
    cribing
    -0.09
    çijĹ
    -0.09
    shal
    -0.08
    ually
    -0.08
    POSITIVE LOGITS
    -fashioned
    0.12
    eds
    0.10
    oran
    0.09
    timer
    0.09
    am
    0.09
    möglich
    0.09
    igator
    0.09
    æĮĩçĶ²
    0.09
    entifier
    0.08
    oppel
    0.08
    Activations Density 0.016%

    No Known Activations