© 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. 19-TRANSCODER-HP
    7. 9070
    Prev
    Next
    INDEX
    Explanations

    While

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĸ¼æĺ¯
    -0.28
    äºĨä»ĸçļĦ
    -0.26
    èĥĮåIJİ
    -0.25
    ä¿IJ
    -0.25
    akers
    -0.25
     inf
    -0.24
    èĥĮåIJİçļĦ
    -0.24
    çĸij
    -0.24
    åĽłä¸ºä»ĸ
    -0.24
    ENTS
    -0.24
    POSITIVE LOGITS
    ken
    0.25
    Commerce
    0.25
     mere
    0.25
    .pm
    0.24
    rb
    0.24
    /INFO
    0.24
    lords
    0.23
    commerce
    0.23
     CDDL
    0.23
    nero
    0.23
    Activations Density 1.264%

    No Known Activations