© 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. 161729
    Prev
    Next
    INDEX
    Explanations

    satisfaction

    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
    åİļ
    -0.29
    è¯į
    -0.27
    æ³Ľ
    -0.27
     intim
    -0.26
    iant
    -0.25
     eget
    -0.25
    éĹª
    -0.25
    æĬµ
    -0.25
    åİī
    -0.24
    cae
    -0.24
    POSITIVE LOGITS
     post
    0.29
     dri
    0.28
     s
    0.27
    Regarding
    0.26
     by
    0.25
    mts
    0.25
     sup
    0.25
     regarding
    0.25
     Regarding
    0.25
    éļ¼
    0.24
    Activations Density 0.468%

    No Known Activations