© 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. 142370
    Prev
    Next
    INDEX
    Explanations

    have

    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
     toward
    -0.28
    éĢļ
    -0.27
     Blitz
    -0.26
    ockey
    -0.26
    çIJ¼
    -0.25
    BL
    -0.25
    ToInt
    -0.24
     дол
    -0.24
     tendencies
    -0.24
    port
    -0.23
    POSITIVE LOGITS
    (gp
    0.28
    çĩĶ
    0.26
    _VOID
    0.25
    ãģĿãĤĮ
    0.25
    reste
    0.25
    ç«ĻçĿĢ
    0.24
     spindle
    0.24
    enci
    0.23
    é³ħ
    0.23
    unque
    0.23
    Activations Density 15.000%

    No Known Activations