© 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. 130775
    Prev
    Next
    INDEX
    Explanations

    Islands

    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
    alte
    -0.28
    å®īåħ¨æĦŁ
    -0.26
    æľĢå¿«
    -0.26
    oen
    -0.26
    çĽĨ
    -0.25
    èĬĤ约
    -0.24
    æ·ĸ
    -0.24
    驸
    -0.24
    aldo
    -0.23
     Random
    -0.23
    POSITIVE LOGITS
    atto
    0.30
     Rhodes
    0.28
    åĻ¢
    0.26
    åĽ½äºº
    0.26
    å²Ľä¸Ĭ
    0.26
     attending
    0.26
    夷
    0.26
     "'"
    0.25
    kv
    0.25
    balls
    0.25
    Activations Density 17.203%

    No Known Activations