© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22168
    Prev
    Next
    INDEX
    Explanations

    purpose or intention

    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
    ä½ķåĨµ
    -0.11
    éľĨ
    -0.10
    coe
    -0.10
    ä¸Ģ代
    -0.10
    è¡·
    -0.10
    TRACE
    -0.09
    ½
    -0.09
    riad
    -0.09
    arez
    -0.09
    trail
    -0.09
    POSITIVE LOGITS
    ities
    0.17
    ively
    0.12
    ENDED
    0.10
    ellij
    0.10
    errupt
    0.10
    egrated
    0.10
    ality
    0.10
    ìĤ¬íķŃ
    0.10
    ervals
    0.09
    ãģ¿ãģª
    0.09
    Activations Density 0.022%

    No Known Activations