© 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. 130654
    Prev
    Next
    INDEX
    Explanations

    code files

    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
    æĢ§åij½
    -0.29
    è¾ĩ
    -0.29
    utomation
    -0.28
     grandfather
    -0.24
     Rangers
    -0.24
     инÑĦоÑĢм
    -0.24
     Survival
    -0.23
    Surv
    -0.23
    èĪĨ
    -0.23
    çĶŁåij½
    -0.23
    POSITIVE LOGITS
    å¸Ĥéķ¿
    0.25
    ело
    0.24
    åħ¶ä¸Ń
    0.24
    å¼Ģåĩº
    0.24
    æĹłäºº
    0.23
    åĪĨæѧ
    0.23
    é£İæ°Ķ
    0.23
    è°Ľ
    0.23
    _middle
    0.23
    ç¡Ŀ
    0.23
    Activations Density 26.285%

    No Known Activations