© 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. 107445
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     Auditor
    -0.25
    orda
    -0.25
     Millions
    -0.25
    çļĦåĽłç´ł
    -0.25
     rects
    -0.25
    æŀģéĻIJ
    -0.24
    ilian
    -0.24
    abouts
    -0.24
    ãģĵãģĵãģ¾ãģ§
    -0.24
    åħ±åĴĮ
    -0.24
    POSITIVE LOGITS
    Definition
    0.27
     stand
    0.27
    æĶ¶è´¹æłĩåĩĨ
    0.26
    éĩĩ
    0.26
     targ
    0.26
     неÑĤ
    0.25
    ame
    0.25
    stand
    0.25
    ownt
    0.25
     Definition
    0.24
    Activations Density 13.628%

    No Known Activations