© 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. 130185
    Prev
    Next
    INDEX
    Explanations

    Wanting

    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
    çļĦèĢģ
    -0.24
    移åĬ¨
    -0.24
    keit
    -0.24
    ismet
    -0.24
    -rating
    -0.24
    izers
    -0.23
    çļĦä¸Ģ
    -0.23
     Subway
    -0.23
     reviews
    -0.23
     isp
    -0.23
    POSITIVE LOGITS
    ocol
    0.27
    æĥ³åĬŀæ³ķ
    0.27
    usi
    0.26
    골
    0.26
    oglob
    0.26
    å¸ĮæľĽéĢļè¿ĩ
    0.26
    稿
    0.25
     Vu
    0.25
    esta
    0.25
    æĥ³æī¾
    0.25
    Activations Density 7.712%

    No Known Activations