© 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. 64098
    Prev
    Next
    INDEX
    Explanations

    US patents

    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
    ircles
    -0.29
    falls
    -0.25
    éĿ¢åĮħ
    -0.25
    åĩºåħ¥
    -0.24
    åķĦ
    -0.24
    .catch
    -0.24
    arde
    -0.24
    ahun
    -0.24
    å·²ä¹ħ
    -0.24
    culos
    -0.24
    POSITIVE LOGITS
    rame
    0.28
     Mor
    0.26
    身åŃIJ
    0.25
    éķ«
    0.25
    æ¼Ĥ亮çļĦ
    0.24
    æĶ¶æĭ¾
    0.24
    exterity
    0.24
    .obtain
    0.24
     luxe
    0.23
    .SizeType
    0.23
    Activations Density 35.144%

    No Known Activations