© 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. 130421
    Prev
    Next
    INDEX
    Explanations

    Code, questions about code

    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
    ivid
    -0.26
    plied
    -0.26
    positor
    -0.25
     vap
    -0.25
    umpt
    -0.24
     penetrating
    -0.24
     oily
    -0.24
    身å¿ĥåģ¥åº·
    -0.24
     strength
    -0.24
    esign
    -0.23
    POSITIVE LOGITS
    atsu
    0.27
    unnel
    0.26
     Assign
    0.25
    åıijçĶŁ
    0.25
    rex
    0.25
    ré
    0.25
     contact
    0.24
    çļĦåıijçĶŁ
    0.24
    ungs
    0.24
    ulary
    0.24
    Activations Density 3.588%

    No Known Activations