© 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. 41332
    Prev
    Next
    INDEX
    Explanations

    Technical/descriptive writing

    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
    Begin
    -0.26
    com
    -0.24
     compreh
    -0.24
    æ¶ī
    -0.24
    à¸ķะ
    -0.24
    åıĭè°Ĭ
    -0.23
    Com
    -0.23
     Corner
    -0.23
    yo
    -0.23
    æ®´
    -0.23
    POSITIVE LOGITS
    -factor
    0.26
    ISTA
    0.26
    éĺĬ
    0.26
    opr
    0.25
    oleans
    0.25
    ldata
    0.24
    ÐĵÐŀ
    0.23
    ;↵↵↵↵↵
    0.23
    _OCC
    0.23
    ãģĵãĤĮãģĮ
    0.23
    Activations Density 1.349%

    No Known Activations