© 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. 40264
    Prev
    Next
    INDEX
    Explanations

    legal action

    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
    æľĢéĩįè¦ģçļĦ
    -0.27
    Callable
    -0.25
    æľĢ大çļĦ
    -0.24
     latest
    -0.24
    便
    -0.24
    -remove
    -0.24
     part
    -0.24
     cos
    -0.23
     Singer
    -0.23
    _callable
    -0.23
    POSITIVE LOGITS
    owan
    0.34
    markup
    0.29
    pert
    0.28
    éºĭ
    0.27
    bef
    0.26
    ä¸ĩåı°
    0.26
    èĩº
    0.25
     *@
    0.25
    ROUT
    0.25
     vertically
    0.25
    Activations Density 0.371%

    No Known Activations