© 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. 19-TRANSCODER-HP
    7. 8308
    Prev
    Next
    INDEX
    Explanations

    Question answering/discussions

    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
    INES
    -0.30
    ved
    -0.27
    ines
    -0.26
    Mui
    -0.26
    elly
    -0.25
    illary
    -0.25
     than
    -0.25
    éĥħ
    -0.25
    urity
    -0.24
    ContentSize
    -0.24
    POSITIVE LOGITS
    eyer
    0.29
     TRI
    0.29
    æ£
    0.28
    ixon
    0.28
    ilo
    0.27
    åĩºçİ°åľ¨
    0.27
    æŀ¢
    0.27
     %↵↵
    0.25
     поÑıви
    0.24
    '↵↵
    0.24
    Activations Density 0.267%

    No Known Activations