© 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. 111928
    Prev
    Next
    INDEX
    Explanations

    technical files, medical articles

    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
     Klein
    -0.25
    ä¸ı
    -0.25
    anton
    -0.25
     hooked
    -0.25
     destin
    -0.24
    æĹ¥çĶµ
    -0.24
    åĽ½å®¶çº§
    -0.24
     greatness
    -0.24
    å½ĵäºĭ
    -0.24
    anya
    -0.23
    POSITIVE LOGITS
    inq
    0.24
    vu
    0.24
     mut
    0.24
    ,},↵
    0.24
    .choices
    0.24
     Meer
    0.24
    ")}
    0.23
    ULAR
    0.23
    jis
    0.23
    mund
    0.23
    Activations Density 0.004%

    No Known Activations