© 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. 40375
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    ceso
    -0.25
    éķ¿åº¦
    -0.25
    èµľ
    -0.25
    åĬłå¼º
    -0.25
    èı©èIJ¨
    -0.24
    çīĽå¸Ĥ
    -0.24
    æIJ¦
    -0.24
    ethereum
    -0.24
    å¢ŀ
    -0.24
     ferry
    -0.24
    POSITIVE LOGITS
    haft
    0.31
    hood
    0.27
    åij½åIJį
    0.26
    Owned
    0.26
    Why
    0.25
     named
    0.25
    åį±å®³
    0.25
    hon
    0.25
     ÑģÑĤанд
    0.25
    éļ¨æĻĤ
    0.24
    Activations Density 0.903%

    No Known Activations