© 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. 27307
    Prev
    Next
    INDEX
    Explanations

    rhodium, chronograph, molecular screening

    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
    çĦĻ
    -0.09
    æĶ¶
    -0.09
    举
    -0.09
    å®ģæĦ¿
    -0.08
    èĩªæĪij
    -0.08
    仪
    -0.08
    è´Ńç½®
    -0.08
    æŀģåĬĽ
    -0.08
    æīĥ
    -0.08
    ç³į
    -0.08
    POSITIVE LOGITS
     Shed
    0.10
    éĤ¦
    0.09
    çİ»çĴĥ
    0.09
    é£İ鼨
    0.08
    å®ĺ
    0.08
    ç¤ģ
    0.08
    ç¿»
    0.08
    -quarter
    0.08
    åĬª
    0.08
    èĨ³
    0.08
    Activations Density 0.054%

    No Known Activations