© 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. 22986
    Prev
    Next
    INDEX
    Explanations

    the

    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
    _RULE
    -0.26
    é»ŀ
    -0.26
     FORWARD
    -0.25
    çĤ¹äºĨ
    -0.25
     Wah
    -0.25
    åIJįé¢Ŀ
    -0.24
    |#
    -0.24
    سÙĪر
    -0.24
     Recipe
    -0.24
     WHILE
    -0.24
    POSITIVE LOGITS
    çķĻ
    0.25
    rama
    0.25
     mattresses
    0.25
     exited
    0.24
    çļĦ年轻人
    0.24
    duk
    0.23
    缺ä¹ı
    0.23
    é£ĵ
    0.23
     boo
    0.23
    ê´ij
    0.23
    Activations Density 0.000%

    No Known Activations