© 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. 22-TRANSCODER-HP
    7. 88043
    Prev
    Next
    INDEX
    Explanations

    matter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĬŀæ³ķ
    -0.28
    MAND
    -0.26
    çļĦèīºæľ¯
    -0.26
    spl
    -0.24
    cai
    -0.23
    çģ¾éļ¾
    -0.23
     steer
    -0.23
    åľ¨ä¸Ģ个
    -0.23
     disag
    -0.23
    çħ§
    -0.22
    POSITIVE LOGITS
    izzy
    0.25
    ++++++++++++++++++++++++++++++++
    0.24
    lean
    0.24
    ieres
    0.24
    paced
    0.23
    опеÑĢ
    0.23
    ä¸Ģ声
    0.23
    emonic
    0.23
    大大å°ı
    0.22
    .TRUE
    0.22
    Activations Density 0.111%

    No Known Activations