© 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. 30235
    Prev
    Next
    INDEX
    Explanations

    front followed by a noun or suffix

    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
    esses
    -0.10
    é«ĺéĢŁ
    -0.09
    mps
    -0.09
    èĭ±æĸĩ
    -0.09
    åħįçĸ«åĬĽ
    -0.09
    opensource
    -0.09
    èĩªè´Ł
    -0.09
    æĶ¶ç´§
    -0.09
    otte
    -0.09
    ixon
    -0.09
    POSITIVE LOGITS
    ä»İåīį
    0.09
     front
    0.09
    åĬŀ
    0.08
     Front
    0.08
    浪
    0.08
    寡
    0.08
    tek
    0.08
    paged
    0.07
    -front
    0.07
    MMM
    0.07
    Activations Density 0.023%

    No Known Activations