© 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. 27951
    Prev
    Next
    INDEX
    Explanations

    jerusalem and corinth

    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
    们
    -0.12
    è¡Ļ
    -0.09
    ạm
    -0.09
    ez
    -0.09
    ä¸ĵ人
    -0.09
    agem
    -0.09
    ees
    -0.09
    èħ°éĥ¨
    -0.08
    OfYear
    -0.08
    å¨ĵ
    -0.08
    POSITIVE LOGITS
    åŀĵ
    0.09
    å®ļå±ħ
    0.08
    pekt
    0.08
    anka
    0.08
    ows
    0.08
    çĬ¹
    0.08
    ä¸īåįĥ
    0.08
    ibrated
    0.08
    丸
    0.08
    çŃīåľ°
    0.08
    Activations Density 0.005%

    No Known Activations