© 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. 14-TRANSCODER-HP
    7. 39962
    Prev
    Next
    INDEX
    Explanations

    planning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸Ģæīĭ
    -0.28
    æĢ»ä½ĵè§ĦåĪĴ
    -0.27
     undergrad
    -0.26
    pedia
    -0.26
    ward
    -0.26
    drops
    -0.25
     planning
    -0.25
    agrid
    -0.25
     shorts
    -0.24
    Guard
    -0.24
    POSITIVE LOGITS
     Presence
    0.28
    à¤Ŀ
    0.27
    imat
    0.26
    HttpContext
    0.24
    ÑĮе
    0.24
    /pkg
    0.24
    orem
    0.24
    (sd
    0.23
     presence
    0.23
    æİ¨è¿Ł
    0.23
    Activations Density 3.048%

    No Known Activations