© 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. 40901
    Prev
    Next
    INDEX
    Explanations

    president

    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
    éĵ¸
    -0.31
    abin
    -0.29
    è·µ
    -0.28
    æģ¶éŃĶ
    -0.28
    æĩ
    -0.27
    ä»Ģä¹ĪåİŁåĽł
    -0.26
     forgive
    -0.26
     fatalError
    -0.26
    宽
    -0.25
    èł¢
    -0.25
    POSITIVE LOGITS
    infra
    0.29
    Electric
    0.27
     electric
    0.27
     Electric
    0.26
    代çIJĨ
    0.26
    ãģĿ
    0.25
    rated
    0.25
    (Tree
    0.25
    electric
    0.25
    alist
    0.25
    Activations Density 3.258%

    No Known Activations