© 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. 50430
    Prev
    Next
    INDEX
    Explanations

    rehabilitation or rehab

    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
    nect
    -0.11
    appen
    -0.11
    orial
    -0.11
    ersion
    -0.10
    filer
    -0.10
    佬
    -0.09
    fos
    -0.09
    ogle
    -0.09
    flake
    -0.09
    felt
    -0.09
    POSITIVE LOGITS
    ilitating
    0.12
    itat
    0.10
    utta
    0.09
    utan
    0.09
    å®īç½®
    0.09
    avia
    0.09
    paren
    0.08
    çĻ½éĽª
    0.08
    çİ°åĩº
    0.08
     tá»ij
    0.08
    Activations Density 0.014%

    No Known Activations