© 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. 20-TRANSCODER-HP
    7. 141686
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     пÑĢедлаг
    -0.26
    .ru
    -0.25
    -anchor
    -0.25
    çĪ¶åŃIJ
    -0.25
     ****************************************************************************
    -0.25
    森
    -0.25
    è¿Ļåı¥è¯Ŀ
    -0.25
    createQuery
    -0.25
    à¹ĩà¸Ļ
    -0.24
     setC
    -0.24
    POSITIVE LOGITS
    iration
    0.28
    vo
    0.27
     convo
    0.26
    si
    0.26
    oud
    0.25
    ayan
    0.25
     civ
    0.25
     passion
    0.25
    Outputs
    0.25
    ensitivity
    0.25
    Activations Density 3.276%

    No Known Activations