© 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. 39604
    Prev
    Next
    INDEX
    Explanations

    gen followed by suffixes or parts of words

    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
    unn
    -0.10
    heid
    -0.09
    teen
    -0.09
    åįļæĸĩ
    -0.09
    iffs
    -0.08
    lications
    -0.08
     männer
    -0.08
    /epl
    -0.08
    ãģĬãĤĪ
    -0.08
    upal
    -0.08
    POSITIVE LOGITS
    éric
    0.11
    ially
    0.10
    ial
    0.09
    çģŃçģ«
    0.08
    ral
    0.08
    lector
    0.08
    ically
    0.08
    etic
    0.08
    omic
    0.08
    faces
    0.08
    Activations Density 0.039%

    No Known Activations