© 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. 20-TRANSCODER-HP
    7. 129821
    Prev
    Next
    INDEX
    Explanations

    conflict

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LocalizedMessage
    -0.27
     uważ
    -0.24
    оÑĩка
    -0.24
     hes
    -0.24
     pass
    -0.24
    ಡ
    -0.24
    æģ¤
    -0.24
    é¼ĵåĬ±
    -0.23
    .findBy
    -0.23
     Finish
    -0.23
    POSITIVE LOGITS
    åıĹåĪ°
    0.27
    ä¸Ńæ¯Ĵ
    0.27
    Cast
    0.25
    åıĹåĪ°äºĨ
    0.25
    Ster
    0.25
    full
    0.24
    åıĻ
    0.24
    “Yes
    0.24
    ï¼ĮåĪĻ
    0.24
     days
    0.23
    Activations Density 12.569%

    No Known Activations