© 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. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 163048
    Prev
    Next
    INDEX
    Explanations

    Physical properties

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĹģ
    -0.32
    é¡»
    -0.28
    uko
    -0.27
    eps
    -0.26
    éģĵ
    -0.26
    éłĪ
    -0.25
    绥
    -0.24
    éĢ»
    -0.24
    æį¢
    -0.24
    åľ¨ä¸Ģ
    -0.23
    POSITIVE LOGITS
    ä¸ĢèĪ¬éĥ½æĺ¯
    0.28
    xac
    0.27
    alars
    0.27
     flat
    0.26
    å·¥ä½ľä½ľé£İ
    0.26
    xBB
    0.25
     levels
    0.25
    Nil
    0.24
     thro
    0.24
    alley
    0.24
    Activations Density 0.008%

    No Known Activations