© 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. 129869
    Prev
    Next
    INDEX
    Explanations

    Prepositions

    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
    inson
    -0.28
     din
    -0.28
     dynamic
    -0.26
    insk
    -0.24
    çĶ·åŃ©åŃIJ
    -0.24
    stab
    -0.24
    庾
    -0.24
    æľĪä¸ĭæŬ
    -0.24
    .eval
    -0.23
    esan
    -0.23
    POSITIVE LOGITS
    лÑĮн
    0.27
    ppers
    0.26
     Brooks
    0.26
    ifiers
    0.26
    éĥ¨ä»¶
    0.26
    ographer
    0.25
    åIJĮèĥŀ
    0.25
    ложениÑı
    0.24
    ä¸Ģ级
    0.24
    èĩªçĶ±è´¸æĺĵ
    0.24
    Activations Density 19.770%

    No Known Activations