© 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. 40868
    Prev
    Next
    INDEX
    Explanations

    code

    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
     example
    -0.36
    ä¾ĭåŃIJ
    -0.35
     exemplo
    -0.33
    example
    -0.32
    Example
    -0.29
    ä¾ĭ
    -0.29
     Beispiel
    -0.29
    为ä¾ĭ
    -0.29
    -example
    -0.28
     Example
    -0.28
    POSITIVE LOGITS
     either
    0.29
    æŃ¤äºº
    0.27
    lopen
    0.25
    (!_
    0.25
    ÑĢÑĥз
    0.24
    grant
    0.24
     Stmt
    0.24
    è¦ģä¹Ī
    0.24
    çļĦåŁºç¡Ģ
    0.24
    alent
    0.23
    Activations Density 1.151%

    No Known Activations