© 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. 9-TRANSCODER-HP
    7. 29512
    Prev
    Next
    INDEX
    Explanations

    power supply/voltage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Thy
    -0.28
     ::::::::
    -0.27
    alsy
    -0.26
    è¯ĬçĸĹ
    -0.25
    cano
    -0.25
    çģµ
    -0.25
    arat
    -0.25
     stray
    -0.25
    rega
    -0.25
     pensé
    -0.24
    POSITIVE LOGITS
    è´¨åľ°
    0.28
    æī«
    0.27
    IKE
    0.26
    odom
    0.25
    IFF
    0.25
    ioned
    0.24
    cplusplus
    0.24
    ä¸Ģè§Ĵ
    0.24
     Ive
    0.24
    PEG
    0.24
    Activations Density 4.771%

    No Known Activations