© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38043
    Prev
    Next
    INDEX
    Explanations

    snowboard, sports, board

    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
     trá»Ŀi
    -0.09
    åĸī
    -0.09
    remen
    -0.09
    å¸Ĩ
    -0.09
    _anchor
    -0.08
    OrDefault
    -0.08
    çĤ¹äºĨçĤ¹å¤´
    -0.08
    éĶ·
    -0.08
    FormGroup
    -0.08
    anchor
    -0.08
    POSITIVE LOGITS
    åij½è¿IJ
    0.08
    t
    0.08
    er
    0.08
    éĥ½æľīçĿĢ
    0.08
    ignum
    0.08
    uration
    0.08
    igans
    0.08
    еÑĢÑĭ
    0.08
    IRO
    0.08
    åıĤä¿Ŀ
    0.07
    Activations Density 0.002%

    No Known Activations