© 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. 61501
    Prev
    Next
    INDEX
    Explanations

    propaganda, prophecy, props

    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
    ãģĦãģĨ
    -0.12
    tings
    -0.12
    -0.11
    íijľ
    -0.11
    ollower
    -0.10
    owing
    -0.10
    าะ
    -0.10
    roring
    -0.09
    ingly
    -0.09
    nger
    -0.09
    POSITIVE LOGITS
    hecy
    0.12
    iedades
    0.11
    folio
    0.10
    inqu
    0.10
    agation
    0.10
     ë¶Ī구íķĺê³ł
    0.10
    ulsive
    0.10
    essor
    0.09
    setter
    0.09
    orz
    0.09
    Activations Density 0.039%

    No Known Activations