© 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. 22801
    Prev
    Next
    INDEX
    Explanations

    big old hard

    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
    PropertyParams
    -0.11
    æĪIJé¾Ļ
    -0.11
    èµĦ产éĩįç»Ħ
    -0.10
    æŃ£æĺ¯åĽłä¸º
    -0.10
    ä¹ĭæīĢ以
    -0.10
    çķıæĥ§
    -0.10
    çļĦæľ¬è´¨
    -0.10
    å¹´è½»çļĦ
    -0.10
    èѦæĸ¹
    -0.09
    以èī²
    -0.09
    POSITIVE LOGITS
    ish
    0.09
    碰
    0.08
    à¹ģà¸ľ
    0.08
    åĵį
    0.07
    lor
    0.07
    orraine
    0.07
    AIN
    0.07
    erson
    0.07
    tero
    0.07
    uncate
    0.07
    Activations Density 0.032%

    No Known Activations