© 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. 108056
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    erb
    -0.25
    åħīéĺ´
    -0.25
    Luc
    -0.24
    æłĩå¿ĹæĢ§
    -0.24
    #{
    -0.23
    ä¸įåħģ许
    -0.23
    }`
    -0.23
     twin
    -0.23
     Tail
    -0.23
    ldr
    -0.23
    POSITIVE LOGITS
    heet
    0.32
     Fo
    0.26
    mpp
    0.26
    cap
    0.25
    ÑģÑĤвÑĥ
    0.24
    ertil
    0.24
    azole
    0.23
     muj
    0.23
    ova
    0.23
    xit
    0.23
    Activations Density 6.174%

    No Known Activations

    This feature has no known activations.