© 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. 33824
    Prev
    Next
    INDEX
    Explanations

    drying and dehydration

    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
    çĥĽ
    -0.11
    éĻħ
    -0.10
    缼
    -0.10
    礼
    -0.10
    åīį沿
    -0.09
    éĹ®åĢĻ
    -0.09
    çŃ¾ç½²äºĨ
    -0.09
    åĽ½å®¶éĩįçĤ¹
    -0.09
     Briggs
    -0.09
    èµ·æºIJ
    -0.08
    POSITIVE LOGITS
    å¹²çĩ¥
    0.21
     drying
    0.19
    çĥĺå¹²
    0.18
     dryer
    0.15
     dried
    0.15
    å¹²
    0.15
     dry
    0.15
    ä¹¾
    0.15
    dry
    0.13
    Dry
    0.13
    Activations Density 0.079%

    No Known Activations