© 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. 129136
    Prev
    Next
    INDEX
    Explanations

    and/plus

    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
    Negative Logits
     kole
    -0.27
    achable
    -0.27
    åı¯è¾¾
    -0.26
    代
    -0.26
     moot
    -0.26
     edged
    -0.25
     |_|
    -0.24
    LIKELY
    -0.24
    ãĤªãĤ¹
    -0.24
    åĨħãģ®
    -0.24
    POSITIVE LOGITS
    å®ĿçŁ³
    0.30
    berman
    0.25
    !(:
    0.24
    ublic
    0.24
    аÑĤÑĥÑĢ
    0.24
    holm
    0.24
    "—
    0.23
    atorio
    0.23
    rement
    0.23
     ÑĢанее
    0.22
    Activations Density 0.038%

    No Known Activations