© 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. 111254
    Prev
    Next
    INDEX
    Explanations

    be

    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
     was
    -0.64
     had
    -0.60
     belonged
    -0.56
    å½ĵæŶ
    -0.55
    å½ĵæŶçļĦ
    -0.53
     бÑĭла
    -0.53
    had
    -0.52
    was
    -0.52
     knew
    -0.51
     бÑĭл
    -0.50
    POSITIVE LOGITS
    .SuspendLayout
    0.38
    даеÑĤÑģÑı
    0.34
    аеÑĤÑģÑı
    0.33
     are
    0.33
     does
    0.32
    ãģĵãģ¨ãĤĤãģĤãĤĬãģ¾ãģĻ
    0.32
     takes
    0.32
    аеÑĤ
    0.31
    are
    0.30
     doesn
    0.30
    Activations Density 0.004%

    No Known Activations