© 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. 19-TRANSCODER-HP
    7. 4822
    Prev
    Next
    INDEX
    Explanations

    Strong emotions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hitch
    -0.27
    çĥĻ
    -0.27
    æī©å¼ł
    -0.27
    尺度
    -0.25
    Invariant
    -0.24
    stash
    -0.24
    urry
    -0.24
     recap
    -0.23
    _attach
    -0.23
    loat
    -0.23
    POSITIVE LOGITS
    æķ´é½IJ
    0.28
    Subviews
    0.24
     Lomb
    0.23
    irs
    0.23
    Ñĥм
    0.23
    --
    0.23
    温æļĸ
    0.23
     tallest
    0.23
    æĦīå¿«
    0.23
    ightly
    0.23
    Activations Density 0.056%

    No Known Activations