© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7092
    Prev
    Next
    INDEX
    Explanations

    commute

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vale
    -0.28
    body
    -0.27
    ãĥĩãĤ¶
    -0.26
    ç³ĸå°¿
    -0.25
    apl
    -0.25
    ys
    -0.25
    身åŃIJ
    -0.25
    çĶ¨äºİ
    -0.24
    output
    -0.24
    .java
    -0.24
    POSITIVE LOGITS
    éļ¾
    0.36
    éļ¾åº¦
    0.35
    æľĢéļ¾
    0.35
    åĽ°éļ¾
    0.31
    éĽ£
    0.30
    ä¸įæĺĵ
    0.30
     difficult
    0.29
    ä¸į容æĺĵ
    0.29
    èī°éļ¾
    0.29
     hurdle
    0.29
    Activations Density 0.272%

    No Known Activations