© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 19204
    Prev
    Next
    INDEX
    Explanations

    nut and bolt restoration

    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
    ../../../
    -0.11
    è¿Ļä¸įæĺ¯
    -0.09
    pra
    -0.08
    avl
    -0.08
    éĴĪ
    -0.08
    !--
    -0.08
    åıªè§ģ
    -0.08
    çĦ°
    -0.08
    ine
    -0.08
    sap
    -0.08
    POSITIVE LOGITS
    çĦ¶æĺ¯
    0.13
    ters
    0.12
    ting
    0.11
    onomy
    0.11
    èļĮ
    0.09
    lify
    0.09
    rients
    0.09
    ãĤ¡
    0.09
    ritional
    0.09
    cess
    0.09
    Activations Density 0.009%

    No Known Activations