© 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. 40835
    Prev
    Next
    INDEX
    Explanations

    legal documents

    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
    _approval
    -0.28
     altında
    -0.28
     allowance
    -0.27
     ÑįлекÑĤÑĢо
    -0.26
    -repeat
    -0.25
     permite
    -0.25
    èĤ¿
    -0.24
    memberOf
    -0.24
    rocess
    -0.24
    -interface
    -0.24
    POSITIVE LOGITS
     BB
    0.28
    BB
    0.27
    اÙĩ
    0.24
    è¨Ģ论
    0.24
     Compar
    0.24
    hir
    0.24
    æŁı
    0.24
     Tenant
    0.23
    око
    0.23
     Friend
    0.23
    Activations Density 0.905%

    No Known Activations