© 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. 12-TRANSCODER-HP
    7. 22930
    Prev
    Next
    INDEX
    Explanations

    Computer usage at night

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pled
    -0.25
    rench
    -0.25
    å²ģæŶ
    -0.25
    .CopyTo
    -0.25
    bero
    -0.24
    že
    -0.24
    adh
    -0.24
    è¾¹çķĮ
    -0.23
    uges
    -0.23
    ÑĪло
    -0.23
    POSITIVE LOGITS
    inded
    0.29
    ernals
    0.27
    §è¡Į
    0.26
    èīºäºº
    0.26
    ä¸Ģæ¢Ŀ
    0.25
    specs
    0.25
    åŀĤ缴
    0.24
     sliders
    0.24
    upert
    0.24
     Arbor
    0.24
    Activations Density 0.000%

    No Known Activations