© 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. 55896
    Prev
    Next
    INDEX
    Explanations

    priority

    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
    åĦ¿
    -0.10
    mpp
    -0.09
    ness
    -0.09
    .spatial
    -0.09
    uber
    -0.08
    alter
    -0.08
    cher
    -0.08
    orian
    -0.08
    noop
    -0.08
    aring
    -0.08
    POSITIVE LOGITS
    ente
    0.12
    ìĤ¬íķŃ
    0.11
    구
    0.10
    -setting
    0.10
    ìĪľ
    0.10
    eer
    0.09
    èĵ¼
    0.09
     им
    0.09
    IMIZE
    0.09
    ä»ĺãģij
    0.09
    Activations Density 0.017%

    No Known Activations