© 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. 39901
    Prev
    Next
    INDEX
    Explanations

    Mixed-source or machine-generated content

    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
    spin
    -0.28
    veillance
    -0.27
    aret
    -0.26
     spin
    -0.26
     pry
    -0.26
    cke
    -0.25
    夹
    -0.25
    å¼ķæĵİ
    -0.24
    ä¿Ŀå®Ī
    -0.24
    inding
    -0.24
    POSITIVE LOGITS
    æĪij对
    0.30
    æĪijä¼ļ
    0.28
    æĪijåľ¨
    0.26
    hil
    0.25
    trä
    0.25
     contrast
    0.25
     stump
    0.25
    éĻĽä¸ĭ
    0.24
    ç°¿
    0.24
    IONS
    0.24
    Activations Density 1.046%

    No Known Activations