© 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. 8577
    Prev
    Next
    INDEX
    Explanations

    Sequence or ranking

    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
    踪
    -0.29
    oop
    -0.29
    pond
    -0.28
    èĢĮçİ°åľ¨
    -0.28
     caut
    -0.27
    åĪĿ次
    -0.27
    éĻ¤æѤ
    -0.26
    stag
    -0.26
    turnstile
    -0.26
    VID
    -0.26
    POSITIVE LOGITS
     family
    0.26
    TR
    0.26
     linking
    0.26
    ä¸Ńè¶ħ
    0.26
     interval
    0.25
    instein
    0.25
     manager
    0.25
     collision
    0.24
    åħ³ç³»
    0.24
    仿
    0.24
    Activations Density 0.040%

    No Known Activations