© 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. 4552
    Prev
    Next
    INDEX
    Explanations

    healthy people, behaviors, relationships, snack

    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
    matic
    -0.10
    亲çĪ±
    -0.10
    wise
    -0.10
    erial
    -0.09
    祯
    -0.09
    nit
    -0.09
    cie
    -0.09
    n
    -0.08
    oooooooo
    -0.08
    èѬ
    -0.08
    POSITIVE LOGITS
    -looking
    0.12
    ä¸İåIJ¦
    0.12
    NESS
    0.12
    Enough
    0.12
    -minded
    0.11
    -ish
    0.11
    ëģĶ
    0.11
    awei
    0.11
    ish
    0.10
     enough
    0.10
    Activations Density 0.016%

    No Known Activations