© 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. 141184
    Prev
    Next
    INDEX
    Explanations

    conditions, circumstances

    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
    igion
    -0.26
    è¯ģåĪ¸äº¤æĺĵ
    -0.26
     ance
    -0.25
    ä¸Ńæĸ°
    -0.25
    èµĽåIJİ
    -0.25
    ↵                ↵
    -0.25
     grandson
    -0.24
     uc
    -0.24
    acios
    -0.24
    uyen
    -0.24
    POSITIVE LOGITS
    Thu
    0.30
    åŀĽ
    0.27
    çĶ¸
    0.27
    nonce
    0.26
    ç»Ĵ
    0.26
     Wh
    0.25
     whisper
    0.25
    annel
    0.25
    å¾Ħ
    0.24
    æ¶Į
    0.24
    Activations Density 16.328%

    No Known Activations