© 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. 40260
    Prev
    Next
    INDEX
    Explanations

    Names of women

    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
    åī§åľº
    -0.28
    åī¯
    -0.26
    ä¸ĢæĹı
    -0.26
    æľªå©ļ
    -0.25
    _PE
    -0.25
     trag
    -0.24
    mith
    -0.24
    itemap
    -0.24
    å«Ĥ
    -0.24
    ç¼Ŀ
    -0.23
    POSITIVE LOGITS
    cken
    0.31
     cracking
    0.27
     delegation
    0.26
    eltas
    0.26
    icals
    0.25
     Oasis
    0.25
    lord
    0.24
     general
    0.24
     intr
    0.24
    ῦ
    0.24
    Activations Density 0.108%

    No Known Activations