© 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. 40656
    Prev
    Next
    INDEX
    Explanations

    Code and choices

    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
    å¹³åĿĩæ°´å¹³
    -0.25
     ÑħоÑĤиÑĤе
    -0.24
    çļĦ年轻人
    -0.24
    дÑĥ
    -0.23
    ohl
    -0.23
    Rank
    -0.23
    icamente
    -0.23
     Olson
    -0.23
    è°
    -0.23
    å¦Ĥæŀľä½łæĥ³
    -0.23
    POSITIVE LOGITS
    責
    0.28
    "><!--
    0.26
    -prefix
    0.26
     targ
    0.26
    ãĥĻãĥ¼ãĤ¹
    0.25
    æĺĵ
    0.25
    Interop
    0.25
    ɵ
    0.25
    irut
    0.24
    åĽº
    0.24
    Activations Density 0.232%

    No Known Activations