© 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. 22680
    Prev
    Next
    INDEX
    Explanations

    wave related concepts

    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
    cken
    -0.10
    aurus
    -0.10
    ctl
    -0.09
    ads
    -0.09
    oner
    -0.09
    wine
    -0.09
    PointerException
    -0.08
    _VOL
    -0.08
    ship
    -0.08
    -pages
    -0.08
    POSITIVE LOGITS
    guide
    0.13
    front
    0.12
    backs
    0.12
    lets
    0.11
     goodbye
    0.11
    forms
    0.11
    peed
    0.09
    оÑĩек
    0.09
    обÑĢаз
    0.09
    çĹ¢
    0.09
    Activations Density 0.034%

    No Known Activations