© 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. 17131
    Prev
    Next
    INDEX
    Explanations

    progressive fusion

    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
    æĭīåĬ¨
    -0.09
    -0.09
    åIJ¸
    -0.08
    uttle
    -0.08
    åĸĨ
    -0.08
    åĪ®
    -0.08
     carrier
    -0.08
    æī¿è½½
    -0.08
    Carrier
    -0.08
     Carrier
    -0.08
    POSITIVE LOGITS
    èĪµ
    0.11
    èĽĭ
    0.10
    éģŃåĪ°
    0.09
    æĻ¦
    0.09
    åĶ³
    0.09
    çĶµåİĤ
    0.09
    éģŃ
    0.09
    å·½
    0.09
    ä¸Ģåı£æ°Ķ
    0.08
    大åĶIJ
    0.08
    Activations Density 0.110%

    No Known Activations