© 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. 22-TRANSCODER-HP
    7. 87088
    Prev
    Next
    INDEX
    Explanations

    non-English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åħ¹
    -0.29
     tap
    -0.27
    ule
    -0.27
    uer
    -0.25
     taps
    -0.25
    ä¸Ģ级
    -0.25
     oz
    -0.25
    eid
    -0.25
    uds
    -0.24
     ei
    -0.24
    POSITIVE LOGITS
    çļĦ巨大
    0.27
    被æĬĵ
    0.25
    派人
    0.25
    èĢ»
    0.24
     huh
    0.24
    -Semitic
    0.24
     GdaÅĦsk
    0.24
    巨大
    0.24
    entropy
    0.23
    arians
    0.23
    Activations Density 0.007%

    No Known Activations