© 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. 141767
    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
     End
    -0.29
    otten
    -0.28
     end
    -0.27
    end
    -0.27
    è¶Ĭ
    -0.26
     rains
    -0.26
    End
    -0.25
    endor
    -0.25
    ä»Ģä¹Īäºĭ
    -0.24
    ren
    -0.23
    POSITIVE LOGITS
     Seks
    0.29
    æIJľ
    0.28
     Mur
    0.26
     GtkWidget
    0.25
    楼ä¸ĭ
    0.24
    è´
    0.24
    _DRIVE
    0.24
     Sofa
    0.24
    è£ĺ
    0.24
     grub
    0.24
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.