© 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. 40519
    Prev
    Next
    INDEX
    Explanations

    awards and nominations

    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
    å¿ĥè·³
    -0.27
    æĦŁåħ´è¶£çļĦ
    -0.27
     strains
    -0.26
    ç§ĺ
    -0.25
    çľĭä»ĸ
    -0.25
    æľĢå¤ļçļĦ
    -0.25
    -corner
    -0.25
    è¦ģ害
    -0.25
    Winner
    -0.24
    ç¿Į
    -0.24
    POSITIVE LOGITS
    .widgets
    0.28
     orth
    0.27
    .Imp
    0.26
     Tanz
    0.26
    Cit
    0.25
    磫
    0.24
    æĿijæĿijæ°ij
    0.24
    !(
    0.24
    erg
    0.24
    aravel
    0.23
    Activations Density 0.067%

    No Known Activations