© 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. 57935
    Prev
    Next
    INDEX
    Explanations

    freshman followed by role or time

    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
    çĥ¦
    -0.12
    orsche
    -0.10
    æłĸ
    -0.10
    åİĮæģ¶
    -0.09
    ت
    -0.09
    çIJ´
    -0.09
    æŁĦ
    -0.09
    Ãłi
    -0.09
    ted
    -0.09
    lices
    -0.09
    POSITIVE LOGITS
    -most
    0.11
    涯
    0.11
    nas
    0.09
    ep
    0.09
    hol
    0.08
    st
    0.08
    hood
    0.08
    éªħ
    0.08
    [F
    0.08
    ems
    0.08
    Activations Density 0.003%

    No Known Activations