© 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. 112255
    Prev
    Next
    INDEX
    Explanations

    been

    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
     Exped
    -0.26
     challenger
    -0.25
    .Gray
    -0.24
    æıĽ
    -0.24
     mechan
    -0.24
     exped
    -0.24
    jest
    -0.24
    jour
    -0.24
    .patch
    -0.24
     Seven
    -0.23
    POSITIVE LOGITS
    inh
    0.26
    dera
    0.25
    inho
    0.25
    gar
    0.25
    urret
    0.24
    æĭĸæ¬ł
    0.24
    èĬĺ
    0.23
    (InputStream
    0.23
    èĢģæĿ¿
    0.23
    å°ĸ
    0.23
    Activations Density 0.048%

    No Known Activations