© 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. 33891
    Prev
    Next
    INDEX
    Explanations

    throat

    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
    -0.12
    ãģ¹ãģį
    -0.11
    --------------------------------
    -0.11
    ----------------
    -0.09
    itor
    -0.09
    ult
    -0.09
    fred
    -0.08
    nection
    -0.08
    ritte
    -0.08
    heid
    -0.08
    POSITIVE LOGITS
    lessly
    0.11
    ingly
    0.11
    less
    0.10
    fulness
    0.09
    iness
    0.09
    REAT
    0.09
    lace
    0.09
    ened
    0.09
    alian
    0.09
    воÑĢ
    0.09
    Activations Density 0.016%

    No Known Activations