© 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. 41002
    Prev
    Next
    INDEX
    Explanations

    are

    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
    typings
    -0.28
     Votes
    -0.26
    viron
    -0.24
    缮åħī
    -0.24
     hätte
    -0.24
    æĢĢæĬ±
    -0.24
    âĢ¦.↵↵
    -0.24
    llib
    -0.23
    arrants
    -0.23
    HAV
    -0.23
    POSITIVE LOGITS
    é¹Ĭ
    0.28
    éĻIJæŶ
    0.28
    éĥ½ä¸įæĺ¯
    0.27
    åIJİæľŁ
    0.27
    è·³
    0.26
    Plug
    0.26
    åĵ¦
    0.26
    á»IJ
    0.26
    0.24
    -ish
    0.24
    Activations Density 1.029%

    No Known Activations