© 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. 49216
    Prev
    Next
    INDEX
    Explanations

    size

    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
    顺çķħ
    -0.09
    æľĢå¿«
    -0.08
    å½°
    -0.08
    èľķåıĺ
    -0.08
    çŀİ
    -0.08
    stants
    -0.08
    ä¹±
    -0.08
    _faces
    -0.07
    åĽŀé¦Ī
    -0.07
    .transparent
    -0.07
    POSITIVE LOGITS
    尺寸
    0.19
     size
    0.18
    ãĤµãĤ¤ãĤº
    0.17
     Size
    0.17
    Size
    0.17
    size
    0.16
     sizes
    0.16
    _size
    0.16
     newSize
    0.15
    	size
    0.15
    Activations Density 0.335%

    No Known Activations