© 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. 97809
    Prev
    Next
    INDEX
    Explanations

    provided

    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
    çĶ¨æīĭ
    -0.26
    avra
    -0.25
    æĺŁçIJĥ
    -0.25
    dera
    -0.23
    iving
    -0.23
    å¹¶åľ¨
    -0.23
    ebra
    -0.23
    åĿ¡
    -0.23
    iid
    -0.23
     Institution
    -0.23
    POSITIVE LOGITS
    lijk
    0.28
    axed
    0.28
     enjo
    0.25
    絡
    0.25
     enough
    0.24
    人æŃ»äº¡
    0.24
    ritch
    0.24
     someone
    0.24
    leon
    0.23
    æľī人
    0.23
    Activations Density 0.012%

    No Known Activations