© 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. 23291
    Prev
    Next
    INDEX
    Explanations

    holidays and specific days

    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
    èĮ«çĦ¶
    -0.10
    ogl
    -0.10
    çł´äº§
    -0.10
    èij¬
    -0.09
    åį¯
    -0.09
    年代
    -0.09
    èħĬ
    -0.09
    éºĭ
    -0.09
    éķĿ
    -0.09
    èĥ§
    -0.09
    POSITIVE LOGITS
    åīįå¤ķ
    0.10
    alus
    0.10
    ä¼ij
    0.09
    dra
    0.09
    åħ¨åĽ½äººæ°ij
    0.09
    صÙĪر
    0.08
    éĻĦè¿ij
    0.08
    olu
    0.08
    erson
    0.08
    _Impl
    0.08
    Activations Density 0.018%

    No Known Activations