© 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. 130253
    Prev
    Next
    INDEX
    Explanations

    Code/Programming

    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
    èĢĮåĩº
    -0.28
    >Lorem
    -0.28
    ertype
    -0.27
    boards
    -0.24
     deltaTime
    -0.23
     matt
    -0.23
    ||↵
    -0.23
    andan
    -0.23
    ->$
    -0.23
    >An
    -0.23
    POSITIVE LOGITS
    ly
    0.48
    gether
    0.46
    ï¸ı
    0.42
    theless
    0.41
    self
    0.40
    ive
    0.40
    thing
    0.40
    æŃ¤åŁºç¡Ģä¸Ĭ
    0.40
    istrator
    0.38
    s
    0.38
    Activations Density 0.138%

    No Known Activations