© 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. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 87189
    Prev
    Next
    INDEX
    Explanations

    positive emotions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĢĴ
    -0.27
    etsk
    -0.26
    人æŃ»äº¡
    -0.25
    thood
    -0.24
    LETE
    -0.24
    çľĩ
    -0.23
    åij½åIJį为
    -0.23
    箨
    -0.23
    æ¼ıæ°´
    -0.23
    .override
    -0.23
    POSITIVE LOGITS
    表æĥħ
    0.38
    ç¥ŀæĥħ
    0.36
    æĥħ绪
    0.31
     smile
    0.31
    ç¬ij
    0.30
    æ²īé»ĺ
    0.29
     smiles
    0.29
     reactions
    0.27
     Quiet
    0.27
     reaction
    0.26
    Activations Density 0.004%

    No Known Activations