© 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. 97986
    Prev
    Next
    INDEX
    Explanations

    Narrative, informational 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
    央
    -0.28
     yansı
    -0.25
     tuần
    -0.24
    éĩįçİ°
    -0.24
    shaw
    -0.23
    .ResponseWriter
    -0.23
    æĹĦ
    -0.23
    essor
    -0.23
    åijĪçİ°
    -0.23
    edly
    -0.23
    POSITIVE LOGITS
     flo
    0.27
    ute
    0.26
    otive
    0.25
     el
    0.24
    ilit
    0.24
     misled
    0.23
     mute
    0.23
     logistic
    0.23
    å¾Ĺ罪
    0.23
    иÑĩеÑģкиÑħ
    0.23
    Activations Density 0.022%

    No Known Activations