© 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. 4664
    Prev
    Next
    INDEX
    Explanations

    episode number

    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
    è¿Ļ份
    -0.10
    å¥ij
    -0.10
    å¥ij约
    -0.10
    éĶ¢
    -0.09
    sam
    -0.08
    缸è¿ij
    -0.08
    èĤĩ
    -0.08
    IRT
    -0.08
    åģ¾
    -0.08
    fo
    -0.08
    POSITIVE LOGITS
     episode
    0.18
     episodes
    0.16
    episode
    0.14
    Episode
    0.14
    ä¸ĢæľŁ
    0.14
     Episode
    0.13
    isode
    0.13
    _episode
    0.13
     Episodes
    0.13
    isodes
    0.12
    Activations Density 0.116%

    No Known Activations