© 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. 22849
    Prev
    Next
    INDEX
    Explanations

    overnight

    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
    hone
    -0.28
    ниÑĨа
    -0.28
    æħĿ
    -0.27
    еÑĢÑĭ
    -0.27
    à¹Ģà¸ķ
    -0.27
    ниÑĨ
    -0.26
    éĻĨ
    -0.25
    ä¹Łæ²¡æľī
    -0.25
    odian
    -0.25
    rics
    -0.25
    POSITIVE LOGITS
     bied
    0.26
     Barg
    0.26
     Gaines
    0.24
    coes
    0.24
     Emer
    0.24
    æĭĮ
    0.24
    \grid
    0.24
    岿
    0.23
     lifes
    0.23
    mAh
    0.23
    Activations Density 0.002%

    No Known Activations