© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52449
    Prev
    Next
    INDEX
    Explanations

    material properties and types

    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
    ingly
    -0.10
     Sen
    -0.09
    çĶ¨æ°´
    -0.08
     mere
    -0.08
     ÑĨелÑĮ
    -0.08
    ë§IJ
    -0.08
    agina
    -0.08
     CSRF
    -0.08
    对èĩªå·±
    -0.08
    è¯įæĿ¡
    -0.08
    POSITIVE LOGITS
    温åĴĮ
    0.11
    èĤĦ
    0.10
    èĶ¬
    0.10
    ве
    0.09
    温
    0.09
    質
    0.09
    Hospital
    0.08
    é³ħ
    0.08
    ummies
    0.08
    _ROUT
    0.08
    Activations Density 0.026%

    No Known Activations