© 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. 111555
    Prev
    Next
    INDEX
    Explanations

    any

    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
     remembers
    -0.27
    è®°å¿Ĩ
    -0.27
    :]↵
    -0.26
    ç§ī
    -0.26
    mentation
    -0.26
    RICT
    -0.25
    :]↵↵
    -0.25
    .webkit
    -0.25
    UILD
    -0.24
    enuity
    -0.24
    POSITIVE LOGITS
    odi
    0.27
    ä¹Łæĺ¯ä¸Ģ个
    0.27
    ind
    0.26
    è¦ģåѦä¼ļ
    0.25
    è¦ģåģļ好
    0.25
    ç¶ļãģĦãģ¦
    0.25
     fore
    0.25
    è¦ģåıĬæŶ
    0.24
    uka
    0.24
    NamedQuery
    0.24
    Activations Density 0.001%

    No Known Activations