© 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. 23066
    Prev
    Next
    INDEX
    Explanations

    prices and monetary values

    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
    å°įæĸ¼
    -0.09
    assy
    -0.09
    _chan
    -0.09
    对äºİ
    -0.08
    avel
    -0.08
    _extent
    -0.08
    wor
    -0.08
    subj
    -0.08
    EMENT
    -0.08
    завиÑģ
    -0.08
    POSITIVE LOGITS
    çĶļ
    0.11
     sake
    0.11
    å°Ĩè¿Ľä¸ĢæŃ¥
    0.10
     purposes
    0.10
    å¼Ģå±ķäºĨ
    0.09
    触åĬ¨
    0.09
    æĬĬæĪij
    0.09
    åĽ½å®ī
    0.09
    å°¸
    0.09
    ä¹°äºĨ
    0.08
    Activations Density 0.023%

    No Known Activations