© 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. 5395
    Prev
    Next
    INDEX
    Explanations

    Samsung Galaxy devices

    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
    工夫
    -0.09
    Ùħض
    -0.09
    isci
    -0.08
    æĢ
    -0.08
    ære
    -0.08
    ature
    -0.08
     Jehovah
    -0.08
    ми
    -0.08
    ael
    -0.08
     sublime
    -0.08
    POSITIVE LOGITS
    wich
    0.12
    çķĢ
    0.09
    ry
    0.08
    å½ĵéĢī
    0.08
    pto
    0.08
    åĵĻ
    0.08
    brig
    0.08
    alous
    0.08
    说åĪ°
    0.08
    å¹´æľ«
    0.08
    Activations Density 0.006%

    No Known Activations