© 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. 33-TRANSCODER-HP
    7. 54049
    Prev
    Next
    INDEX
    Explanations

    scientific papers/URLs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anic
    -0.29
    èŁĭ
    -0.26
     trailer
    -0.26
    eve
    -0.26
    ech
    -0.26
    éļĬ
    -0.26
     ric
    -0.25
    dig
    -0.25
    ei
    -0.25
    yum
    -0.25
    POSITIVE LOGITS
    çļĦ大
    0.31
    大
    0.29
    äºĨä¸Ģ
    0.29
    æĭ©
    0.27
    涨
    0.27
    èIJ½
    0.27
    unt
    0.26
    示
    0.26
    é¢ĺ
    0.26
    æĶ¹
    0.26
    Activations Density 0.023%

    No Known Activations