© 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. 62632
    Prev
    Next
    INDEX
    Explanations

    to + verb

    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
    arks
    -0.12
    åı£å¤´
    -0.10
    åªĴä»ĭ
    -0.10
    MENTS
    -0.09
    导å¸Ī
    -0.09
    çŃī级
    -0.09
    LayoutInflater
    -0.09
    .buf
    -0.09
    ãĥIJãĥ©
    -0.09
    _FREQUENCY
    -0.09
    POSITIVE LOGITS
    ä½Ĩåį´
    0.10
    纪
    0.09
    à¹Ħหม
    0.09
    ä½ĵä¼ļ
    0.08
     Pot
    0.08
    ä¸įéĻIJ
    0.08
     pot
    0.08
    çļĩåĨł
    0.08
     bik
    0.08
    ä¸įçĶ¨
    0.08
    Activations Density 0.024%

    No Known Activations