© 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. 34051
    Prev
    Next
    INDEX
    Explanations

    stories and buildings

    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
    çĹ£
    -0.10
    FML
    -0.09
    thane
    -0.09
    æĭĬ
    -0.08
    ference
    -0.08
    çĥŃçĤ¹
    -0.08
    ALLE
    -0.08
    壤
    -0.08
    aland
    -0.08
    å·¥ä½ľå®¤
    -0.08
    POSITIVE LOGITS
    大åݦ
    0.16
    é«ĺ楼
    0.14
    建çŃij
    0.14
     building
    0.14
    çŃij
    0.13
     tower
    0.13
    楼æĪ¿
    0.13
    åĢĴå¡Į
    0.13
    ç»ĵæŀĦ
    0.13
    ä¸Ģæłĭ
    0.12
    Activations Density 0.050%

    No Known Activations