© 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. 31621
    Prev
    Next
    INDEX
    Explanations

    seedlings and young plants

    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
    驾é©Ń
    -0.10
     acted
    -0.09
    æŀī
    -0.09
    大å¦Ī
    -0.09
    åģľæĶ¾
    -0.09
    ALIGN
    -0.08
    доÑĢ
    -0.08
    .act
    -0.08
    enance
    -0.08
    æIJł
    -0.08
    POSITIVE LOGITS
    å´½
    0.13
    èĭĹ
    0.13
    èĭĹæľ¨
    0.12
    çĬĬ
    0.10
    ling
    0.10
    éĽı
    0.10
    å¨ĥå¨ĥ
    0.10
    ç¨ļ
    0.10
    å®Ŀå®Ŀ
    0.09
     offspring
    0.09
    Activations Density 0.098%

    No Known Activations