© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9647
    Prev
    Next
    INDEX
    Explanations

    morph- related 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
    à¹ĥà¸Ī
    -0.10
    atu
    -0.09
    adge
    -0.09
    .createObject
    -0.09
    峪
    -0.09
    ises
    -0.09
    worthy
    -0.09
    oner
    -0.09
    ì±Ħ
    -0.09
    Americ
    -0.09
    POSITIVE LOGITS
    morph
    0.09
    itecture
    0.09
    ysical
    0.09
    sim
    0.09
    åĨį说
    0.08
    å¤ļæł·
    0.08
    åĸĥ
    0.08
    ulario
    0.08
    寡
    0.08
    loom
    0.08
    Activations Density 0.076%

    No Known Activations