© 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. 30647
    Prev
    Next
    INDEX
    Explanations

    hands-on

    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
    sWith
    -0.11
    ssid
    -0.10
    æĺİçıł
    -0.10
    .ExecuteReader
    -0.09
    ss
    -0.09
    ssi
    -0.09
    isphere
    -0.09
    asury
    -0.09
    åħ´
    -0.09
    ninger
    -0.09
    POSITIVE LOGITS
    ðŁı»
    0.11
    chied
    0.10
    heets
    0.09
    cape
    0.09
    -on
    0.09
    çĮ·
    0.08
    çĹĴ
    0.08
    ome
    0.08
    ources
    0.08
    ourced
    0.08
    Activations Density 0.082%

    No Known Activations