© 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. 35-TRANSCODER-HP
    7. 40254
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olas
    -0.27
     way
    -0.27
    æĬ¤æłı
    -0.27
    @
    -0.26
    åĨ°ç®±
    -0.26
     portable
    -0.26
    č↵č↵č↵
    -0.26
     hit
    -0.25
    ï¼Ī
    -0.25
     üzer
    -0.24
    POSITIVE LOGITS
    gis
    0.25
    zos
    0.25
    çĮ¥
    0.25
    ±Ð¾ÑĤ
    0.24
    ä¸įåģľ
    0.24
    -INF
    0.23
     Uno
    0.23
    ä¸įåģľçļĦ
    0.23
     Phrase
    0.23
    éĺµ
    0.23
    Activations Density 4.092%

    No Known Activations

    This feature has no known activations.