© 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. 23948
    Prev
    Next
    INDEX
    Explanations

    doing

    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
     ëĵ¤
    -0.27
    cente
    -0.26
    æĬĺ
    -0.24
    SENT
    -0.24
    -BEGIN
    -0.24
    alem
    -0.24
    èĢķåľ°
    -0.24
    outdir
    -0.24
    çļĦæīĢæľī
    -0.24
     Chapel
    -0.23
    POSITIVE LOGITS
    oard
    0.27
    ç´§
    0.26
    æĪĺæĸĹ
    0.25
     hảo
    0.25
    ÂŃtion
    0.25
    å¹¿æ³ĽçļĦ
    0.25
    æĪij个人
    0.25
    notice
    0.24
    çݰ代
    0.24
    夫
    0.24
    Activations Density 0.000%

    No Known Activations