© 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. 41228
    Prev
    Next
    INDEX
    Explanations

    This and quotation marks

    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
    lay
    -0.27
    æĭIJ
    -0.26
     salon
    -0.26
     dos
    -0.25
    arpa
    -0.24
    زÙĬÙĨ
    -0.24
    é¼İ
    -0.24
    eln
    -0.24
    è¡Ľ
    -0.24
    cbd
    -0.24
    POSITIVE LOGITS
    è¹Ĭ
    0.25
    éŃĶ
    0.24
    天ä¸Ĭ
    0.24
    еÑģÑĮ
    0.23
     yat
    0.23
     equivalent
    0.23
    æĺ¯æ²¡æľī
    0.23
    PASS
    0.23
    ä¸ĸçķĮçļĦ
    0.23
    æĭĺ
    0.23
    Activations Density 0.368%

    No Known Activations