© 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. 22408
    Prev
    Next
    INDEX
    Explanations

    falling

    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
    -opacity
    -0.35
    å¾Ĥ
    -0.30
    æĸ
    -0.28
    æݨ广
    -0.26
    æįŁ
    -0.25
    ÅĤad
    -0.25
     throwError
    -0.24
     marty
    -0.24
    æݨ广åºĶçĶ¨
    -0.24
    stro
    -0.24
    POSITIVE LOGITS
    å·«
    0.26
     RVA
    0.25
     SCRIPT
    0.25
     conf
    0.25
    Submitted
    0.25
     Royals
    0.24
     Plastic
    0.24
    lier
    0.24
    åĪĨæķ£
    0.24
     copper
    0.23
    Activations Density 0.001%

    No Known Activations