© 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. 107670
    Prev
    Next
    INDEX
    Explanations

    self, personal, direct

    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
    lation
    -0.28
     Monk
    -0.26
    aks
    -0.26
     tá»
    -0.26
    汶
    -0.25
    ze
    -0.25
     Ney
    -0.25
    sj
    -0.25
    eva
    -0.25
    .Focus
    -0.24
    POSITIVE LOGITS
    亲èĩª
    0.51
    缴æİ¥
    0.47
     direct
    0.43
     directly
    0.43
     ì§ģìłij
    0.42
     Direct
    0.39
     firsthand
    0.38
    direct
    0.38
    çĭ¬ç«ĭ
    0.37
     OWN
    0.36
    Activations Density 83.515%

    No Known Activations