© 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. 25-TRANSCODER-HP
    7. 107730
    Prev
    Next
    INDEX
    Explanations

    achieving goals

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    责任æĦŁ
    -0.29
    ä¸į符åIJĪ
    -0.28
     cumpl
    -0.26
     Briggs
    -0.25
    TYPES
    -0.24
    completion
    -0.24
     triumph
    -0.24
    è¿Ļæł·è¯´
    -0.24
    è°Īè¯Ŀ
    -0.24
    iya
    -0.23
    POSITIVE LOGITS
    çĭ¬
    0.26
     thi
    0.26
     outstanding
    0.25
    æĹ©æĻļ
    0.24
    )view
    0.24
     Common
    0.23
     updateUser
    0.23
     December
    0.23
    setItem
    0.23
     Ben
    0.23
    Activations Density 0.932%

    No Known Activations