© 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. 51201
    Prev
    Next
    INDEX
    Explanations

    preparation and application of materials

    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
    念
    -0.11
     Overflow
    -0.09
    漪
    -0.09
    agu
    -0.09
    è¡ĮæĶ¿æī§æ³ķ
    -0.08
    æĽ³
    -0.08
    CID
    -0.08
    åı·åı¬
    -0.08
    elho
    -0.08
     Arm
    -0.08
    POSITIVE LOGITS
    æ¸ħæ´ģ
    0.15
    æ¸ħæ´Ĺ
    0.14
    åĩĨå¤ĩå·¥ä½ľ
    0.13
    åĩĨå¤ĩ
    0.13
    å¹²åĩĢ
    0.12
    æ´ĹåĩĢ
    0.12
    æ´ģåĩĢ
    0.12
     preparation
    0.12
     подгоÑĤов
    0.12
     Preparation
    0.11
    Activations Density 0.113%

    No Known Activations