© 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. 32881
    Prev
    Next
    INDEX
    Explanations

    word endings (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
    edException
    -0.11
    หลวà¸ĩ
    -0.11
    umper
    -0.10
    æļ¾
    -0.10
    çĪº
    -0.10
    çĪ·
    -0.10
    åĬ¨çĶŁæĪIJ
    -0.09
    ellaneous
    -0.09
    CloseOperation
    -0.09
    rophe
    -0.09
    POSITIVE LOGITS
    å½ĵä¹ĭ
    0.09
    riv
    0.08
    ÑĤоÑĢ
    0.08
    it
    0.08
    æѤäºĭ
    0.08
    chez
    0.08
    河水
    0.08
    FER
    0.07
    atter
    0.07
    åĬªåĬĽ
    0.07
    Activations Density 0.004%

    No Known Activations