© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 98776
    Prev
    Next
    INDEX
    Explanations

    Scraped online data

    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
    æ½ľ
    -0.31
    ny
    -0.30
    oly
    -0.29
    cape
    -0.29
    æĬĬ
    -0.28
    NG
    -0.28
    icular
    -0.28
    led
    -0.27
    dera
    -0.26
    ollen
    -0.26
    POSITIVE LOGITS
     herself
    0.31
    .did
    0.29
    Leaks
    0.27
    ä½łåºĶ该
    0.27
    让她
    0.25
    èī¯ãģĭãģ£ãģŁ
    0.25
    benchmark
    0.25
    .pathname
    0.25
    åħ©äºº
    0.25
    .flatten
    0.24
    Activations Density 0.008%

    No Known Activations