© 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. 40780
    Prev
    Next
    INDEX
    Explanations

    s

    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
    ologies
    -0.26
    ypass
    -0.26
    èIJ½
    -0.25
    leased
    -0.24
     LAB
    -0.23
    éĦĦ
    -0.23
    mans
    -0.23
    LOOR
    -0.23
    æį®
    -0.22
    ä¸ĢéĿ¢
    -0.22
    POSITIVE LOGITS
    第ä¸ĢæŃ¥
    0.28
     Constitutional
    0.27
    导
    0.25
    /includes
    0.25
    ä¼´éļı
    0.25
    失
    0.24
    åĮħåIJ«
    0.24
    éĽĨåĽ¢èĤ¡ä»½
    0.24
     initially
    0.24
    .Companion
    0.24
    Activations Density 0.170%

    No Known Activations