© 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. 11904
    Prev
    Next
    INDEX
    Explanations

    analog signal or device

    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
    etz
    -0.11
    oted
    -0.10
    ween
    -0.09
    /reset
    -0.09
    clar
    -0.09
    inar
    -0.09
    eld
    -0.09
    ollow
    -0.09
    ened
    -0.09
    çĽ¸ä¿¡
    -0.09
    POSITIVE LOGITS
    ues
    0.15
    oot
    0.11
    ons
    0.10
    auge
    0.10
    ical
    0.10
    gy
    0.10
    å¤Ħå¢ĥ
    0.10
    athon
    0.10
    ities
    0.10
    -aged
    0.10
    Activations Density 0.026%

    No Known Activations