© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 47728
    Prev
    Next
    INDEX
    Explanations

    landing and where it lands

    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
     vig
    -0.09
    媲
    -0.08
    è¢Ĥ
    -0.08
    ä¸Ńè¶ħ
    -0.08
     vigor
    -0.08
    íĥIJ
    -0.08
    èĥ¼
    -0.08
    RIA
    -0.08
    inos
    -0.08
    _MAY
    -0.08
    POSITIVE LOGITS
    èIJ½åľ°
    0.20
     landing
    0.19
     landed
    0.19
    èIJ½åľ¨
    0.17
    landing
    0.17
     Landing
    0.17
    èIJ½åĪ°
    0.16
     lands
    0.15
    èIJ½åħ¥
    0.14
    èIJ½
    0.13
    Activations Density 0.056%

    No Known Activations