© 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. 14-TRANSCODER-HP
    7. 40535
    Prev
    Next
    INDEX
    Explanations

    Time durations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĶĢ
    -0.25
    à¦ĸ
    -0.24
    æ¶ĪéĻ¤
    -0.24
    IRR
    -0.24
    IES
    -0.24
    ä¸īåĪĨ
    -0.23
    è¿Ń
    -0.23
    emi
    -0.23
    ComputedStyle
    -0.23
    ÏĤ
    -0.23
    POSITIVE LOGITS
    guid
    0.28
    å°ıåºĹ
    0.25
    äch
    0.24
    live
    0.24
    cial
    0.24
     aud
    0.23
    uspended
    0.23
    è¯Ħ论
    0.23
     rd
    0.23
     DataView
    0.23
    Activations Density 2.516%

    No Known Activations