© 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. 33400
    Prev
    Next
    INDEX
    Explanations

    per capita, per cent, per annum

    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
    room
    -0.11
    ored
    -0.10
    rist
    -0.10
    /or
    -0.10
    пеÑĢв
    -0.10
    spell
    -0.10
    dır
    -0.09
    te
    -0.09
    rooms
    -0.09
    urance
    -0.09
    POSITIVE LOGITS
     capita
    0.14
    centage
    0.14
    cents
    0.14
     annum
    0.14
    missive
    0.14
    èĩ¾
    0.13
    ceiving
    0.13
    ities
    0.12
    oxide
    0.12
    cep
    0.11
    Activations Density 0.049%

    No Known Activations