© 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. 107851
    Prev
    Next
    INDEX
    Explanations

    Suffixes

    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
    ç´łè´¨æķĻèĤ²
    -0.25
     Tyler
    -0.25
    æľīå¤ļ大
    -0.25
    Tyler
    -0.25
     visible
    -0.24
     altogether
    -0.24
    èĨ¨
    -0.24
    .ds
    -0.23
    Meg
    -0.23
    ESH
    -0.23
    POSITIVE LOGITS
    æ¡£
    0.27
    æĶ¾å¿ĥ
    0.26
    å®īéĺ²
    0.26
    Êĥ
    0.26
    unning
    0.25
     aras
    0.25
    èĦ±
    0.24
     lanes
    0.24
    monic
    0.24
    âľī
    0.24
    Activations Density 26.966%

    No Known Activations