© 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. 161773
    Prev
    Next
    INDEX
    Explanations

    however, but

    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
    lish
    -0.28
    æ¶Īæŀģ
    -0.27
    ä¹Łä¸įæķ¢
    -0.26
    没å¿ħè¦ģ
    -0.26
    mith
    -0.25
    idy
    -0.25
    loth
    -0.25
    ynth
    -0.24
    ESH
    -0.24
     Nou
    -0.24
    POSITIVE LOGITS
     differs
    0.47
     differ
    0.45
     differed
    0.42
    ä¸įä¸Ģæł·
    0.42
    åĮºåĪ«
    0.38
     distingu
    0.36
    ä¸įåIJĮ
    0.34
     differing
    0.33
    unique
    0.33
    çļĦåĮºåĪ«
    0.33
    Activations Density 0.007%

    No Known Activations