© 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. 40281
    Prev
    Next
    INDEX
    Explanations

    Excerpts from documents

    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
    夯
    -0.27
    ä¸Ģ件äºĭæĥħ
    -0.27
    Transport
    -0.25
    è¿IJè¾ĵ
    -0.25
    Increases
    -0.24
     homeowners
    -0.24
    ç»ı
    -0.24
    munition
    -0.24
    éħ±
    -0.24
     disciplined
    -0.23
    POSITIVE LOGITS
    @author
    0.29
    -choice
    0.28
    gens
    0.28
    gnore
    0.27
    xffff
    0.27
    xis
    0.26
    nard
    0.26
    çĮ¿
    0.26
    KI
    0.26
    çŃīå¥ĸ
    0.25
    Activations Density 0.103%

    No Known Activations