© 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. 52920
    Prev
    Next
    INDEX
    Explanations

    Source Code Form or copyright notice

    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
    çĩĥçħ¤
    -0.10
    æݸ
    -0.10
    æĮĩçĶ²
    -0.08
    èĽĩ
    -0.08
    ç½
    -0.08
    èĩªçĦ¶çķĮ
    -0.08
    forth
    -0.08
    мел
    -0.08
    rollable
    -0.08
     pare
    -0.08
    POSITIVE LOGITS
    rush
    0.09
    äº
    0.09
    æĢĢæĬ±
    0.08
    Unload
    0.08
    åİĭåĪ¶
    0.08
    çļĦä¸ľè¥¿
    0.08
     quar
    0.08
    벤
    0.08
    _stuff
    0.08
    å°Ĭ严
    0.08
    Activations Density 0.028%

    No Known Activations