© 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. 22343
    Prev
    Next
    INDEX
    Explanations

    Code

    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
    ño
    -0.30
    è¯ķ
    -0.28
    äºĨå¤ļå°ij
    -0.28
    tti
    -0.28
    istine
    -0.27
    éĶĭ
    -0.27
    hsi
    -0.26
    "net
    -0.25
     upholstery
    -0.25
    sti
    -0.25
    POSITIVE LOGITS
    IMER
    0.29
    æī©
    0.27
     DER
    0.27
    vern
    0.26
    -env
    0.26
    oning
    0.25
     LR
    0.25
     =~
    0.24
     shall
    0.24
    Ậ
    0.24
    Activations Density 0.001%

    No Known Activations