© 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. 51301
    Prev
    Next
    INDEX
    Explanations

    relationship; provider; encounters; link

    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
    isd
    -0.10
    åĪ»
    -0.09
     reducers
    -0.09
    æĩĤäºĭ
    -0.08
    串
    -0.08
    æĭ¬
    -0.08
    碧
    -0.08
    åľ¨å¤ĸ
    -0.08
    åĩ°
    -0.08
    oting
    -0.08
    POSITIVE LOGITS
    å¸ĪçĶŁ
    0.14
    åıĮæĸ¹
    0.13
    åĽĽæĸ¹
    0.12
    åħ³ç³»
    0.11
    å¸Ī
    0.11
    ä¸Ģæĸ¹
    0.10
    WithValue
    0.10
    asz
    0.10
    èµĸ以
    0.10
    ihat
    0.09
    Activations Density 0.088%

    No Known Activations