© 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. 12-TRANSCODER-HP
    7. 23710
    Prev
    Next
    INDEX
    Explanations

    global

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĭIJ
    -0.26
    å®Į
    -0.26
    intern
    -0.25
    åĽ«
    -0.25
     cab
    -0.25
    ç·Ĭ
    -0.25
    Intern
    -0.25
    æľīçļĦ
    -0.25
     Cab
    -0.25
    tournament
    -0.25
    POSITIVE LOGITS
    é¡¿
    0.31
    asured
    0.28
     Approved
    0.27
    å¡«
    0.26
    rices
    0.25
    éłĵ
    0.25
    esters
    0.25
    踵
    0.24
     Checked
    0.24
     Dev
    0.24
    Activations Density 0.013%

    No Known Activations