© 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. 107942
    Prev
    Next
    INDEX
    Explanations

    ads

    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
    ÑĢак
    -0.29
     Kag
    -0.27
     themselves
    -0.24
     Their
    -0.24
     shed
    -0.24
     secret
    -0.24
     pageSize
    -0.24
    near
    -0.24
    /cart
    -0.23
     augmentation
    -0.23
    POSITIVE LOGITS
    itten
    0.30
    UMP
    0.26
    æłĩè®°
    0.26
    lte
    0.26
     emblem
    0.25
    lops
    0.25
    ibus
    0.25
    lands
    0.25
    ToF
    0.25
    ump
    0.25
    Activations Density 14.344%

    No Known Activations