© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 12-TRANSCODER-HP
    7. 24260
    Prev
    Next
    INDEX
    Explanations

    ix

    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
    Negative Logits
    éĢĤ度
    -0.28
    ible
    -0.27
    ison
    -0.26
    ìķł
    -0.26
    loss
    -0.25
    ä¹īåĬ¡æķĻèĤ²
    -0.25
    æįŁ
    -0.24
    standing
    -0.24
    æIJį
    -0.24
     DEALINGS
    -0.24
    POSITIVE LOGITS
    illet
    0.29
     Mesh
    0.29
    opolitan
    0.28
    estic
    0.26
     prop
    0.25
    (prop
    0.25
     éc
    0.25
     Linked
    0.25
    atical
    0.25
    æľīåIJį
    0.24
    Activations Density 0.000%

    No Known Activations