© 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. 20-TRANSCODER-HP
    7. 107219
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     measures
    -0.27
    NAS
    -0.26
    çĽ¸ä¼¼
    -0.25
    asures
    -0.25
    CN
    -0.25
    .getvalue
    -0.24
    ä½ĵ系建设
    -0.24
     cour
    -0.24
     simil
    -0.24
     STDOUT
    -0.24
    POSITIVE LOGITS
    çī¹æ´¾åijĺ
    0.26
     heck
    0.25
    QQ
    0.25
    åį¿
    0.25
    (LayoutInflater
    0.25
     infinity
    0.25
     Bloomberg
    0.24
     assistant
    0.24
    beck
    0.24
    æĬ±
    0.24
    Activations Density 9.526%

    No Known Activations