© 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. 7706
    Prev
    Next
    INDEX
    Explanations

    heat

    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
     Fixture
    -0.26
    æ¶Īè´¹
    -0.26
    æ¶Īè²»
    -0.25
    aday
    -0.24
    zt
    -0.24
    æĽĿåħī
    -0.24
    ophile
    -0.24
    infeld
    -0.24
     Schwarz
    -0.24
     Hundred
    -0.24
    POSITIVE LOGITS
    çļĦ帮åĬ©
    0.25
    åĬĽåѦ
    0.24
    å¤ĸè§Ĥ
    0.24
    suite
    0.24
    aviours
    0.24
    èIJ½
    0.23
     Erie
    0.23
    uite
    0.23
    ç¾Ĭ
    0.23
     attribution
    0.23
    Activations Density 0.014%

    No Known Activations