© 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. 21960
    Prev
    Next
    INDEX
    Explanations

    faith and patience

    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
    ä¸įåıĹ
    -0.12
    åıĺéĢŁ
    -0.09
    èIJ½åľ°
    -0.09
    éĽĩä½£
    -0.09
    åĸĿæ°´
    -0.09
    举æݪ
    -0.09
    éĵī
    -0.09
    å¸IJåı·
    -0.09
    çīĿ
    -0.09
    ertz
    -0.09
    POSITIVE LOGITS
     maturity
    0.10
    quee
    0.09
    pies
    0.09
    çī¹å¾ģ
    0.08
    åħ±
    0.08
    icer
    0.08
     вид
    0.08
    ipline
    0.08
    IFORM
    0.08
    èĻ¹
    0.08
    Activations Density 0.024%

    No Known Activations