© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 12-TRANSCODER-HP
    7. 24225
    Prev
    Next
    INDEX
    Explanations

    computer code strings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     exec
    -0.27
    èļĵ
    -0.26
    ETA
    -0.25
    åĬ²
    -0.25
    å®ŀéĻħæĥħåĨµ
    -0.25
    å¤įåĪ¶
    -0.24
    Æ°á»Łng
    -0.24
    ete
    -0.23
     TPM
    -0.23
    å°±è¿ŀ
    -0.23
    POSITIVE LOGITS
    ç½ijçIJĥ
    0.27
    offline
    0.26
    boys
    0.26
     soaked
    0.26
    erset
    0.25
    struk
    0.25
    bose
    0.25
     Samples
    0.24
    æĽ´é«ĺçļĦ
    0.24
     Boys
    0.24
    Activations Density 0.000%

    No Known Activations