© 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. 3862
    Prev
    Next
    INDEX
    Explanations

    examples (e.g

    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
    pan
    -0.09
    istas
    -0.09
    ning
    -0.08
    çļĦä¸Ģ项
    -0.08
    nal
    -0.08
    type
    -0.08
    lier
    -0.08
    çŃīä¸Ģæī¹
    -0.08
    è¿Ļ对
    -0.08
    ti
    -0.07
    POSITIVE LOGITS
    /GPL
    0.10
    FRING
    0.09
    ä¹Łå°±
    0.09
    å¿ĥè¡Ģ
    0.09
    auge
    0.09
    ipse
    0.09
    ControlEvents
    0.09
    LOCATION
    0.09
    TeX
    0.09
    iesen
    0.09
    Activations Density 0.045%

    No Known Activations