© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8097
    Prev
    Next
    INDEX
    Explanations

    knowledge and information transfer

    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
    åĭĥ
    -0.09
    une
    -0.09
    cargo
    -0.08
    una
    -0.08
     jug
    -0.08
    åĤĢ
    -0.08
    å¤ļäºĨ
    -0.08
    bai
    -0.08
    ught
    -0.07
    å¡ij
    -0.07
    POSITIVE LOGITS
    _bw
    0.09
    缬
    0.09
    足迹
    0.09
    Ñħодим
    0.09
    .Pos
    0.08
    ori
    0.08
    åģļåĪ°äºĨ
    0.08
    itch
    0.08
    illon
    0.08
    å¼Ĥåľ°
    0.08
    Activations Density 1.028%

    No Known Activations