© 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. 40209
    Prev
    Next
    INDEX
    Explanations

    Returning

    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
    inel
    -0.30
    åħ¥åĽŃ
    -0.28
     vent
    -0.26
    çIJ´
    -0.25
    etsk
    -0.25
    ÑĪек
    -0.24
    rupt
    -0.24
    çIJĨ论
    -0.24
    æ±IJ
    -0.23
    ever
    -0.23
    POSITIVE LOGITS
    延伸
    0.27
    legen
    0.26
     ancest
    0.26
    LEG
    0.26
     explan
    0.25
    asctime
    0.25
    æİ¨è¿Ł
    0.25
    imar
    0.24
    夯å®ŀ
    0.24
    dirs
    0.24
    Activations Density 1.522%

    No Known Activations