© 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. 60982
    Prev
    Next
    INDEX
    Explanations

    single people and households

    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
    -rounded
    -0.09
    äºĶçĻ¾
    -0.09
    人æĢ§åĮĸ
    -0.09
    伺æľį
    -0.09
    /help
    -0.09
    icip
    -0.08
    éĢīæĭĶ
    -0.08
    JNI
    -0.08
    ssize
    -0.08
    rend
    -0.08
    POSITIVE LOGITS
    ä¹ħäºĨ
    0.10
    çĬ¶æĢģ
    0.09
    æľªå©ļ
    0.09
    å¤ļå¹´
    0.09
     Scient
    0.09
    åįķ身
    0.09
    çĬ¶æĢģä¸ĭ
    0.09
    зам
    0.09
    ned
    0.09
    èĩªçIJĨ
    0.09
    Activations Density 0.028%

    No Known Activations