© 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. 107484
    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
    dings
    -0.27
    å¥ĸ
    -0.26
    çĶŁ
    -0.25
    çĤ¸å¼¹
    -0.25
    æīŃ
    -0.25
     fault
    -0.23
     TU
    -0.23
    íŤ
    -0.23
    oud
    -0.23
    deaux
    -0.23
    POSITIVE LOGITS
    ammen
    0.30
    AREN
    0.28
    eca
    0.26
    пиÑģÑĭва
    0.26
    ctors
    0.25
    룬
    0.25
    lesi
    0.25
    errs
    0.25
    aman
    0.25
     ostat
    0.25
    Activations Density 0.248%

    No Known Activations

    This feature has no known activations.