© 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. 7522
    Prev
    Next
    INDEX
    Explanations

    Fa followed by specific endings

    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
    hores
    -0.11
    ripper
    -0.10
    оз
    -0.10
    榻
    -0.10
    åĬ©éķ¿
    -0.10
    ãģĹãģ¾ãģĨ
    -0.10
    tures
    -0.09
    åĬŁçĶ¨
    -0.09
    ected
    -0.09
    jamin
    -0.09
    POSITIVE LOGITS
    arb
    0.11
    ience
    0.11
    CTOR
    0.09
    çĻ½é¢Ĩ
    0.09
    илÑĮ
    0.08
    éĹ¾
    0.08
    ../../../
    0.08
    yt
    0.08
    isting
    0.08
    ORN
    0.08
    Activations Density 0.019%

    No Known Activations