© 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. 32-TRANSCODER-HP
    7. 42143
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stra
    -0.34
    æ£ĭ
    -0.31
    .str
    -0.30
    èıľ
    -0.28
     str
    -0.28
    gregate
    -0.27
    bai
    -0.26
    è¯ĦåĪĨ
    -0.26
    æłĩ
    -0.26
    _str
    -0.26
    POSITIVE LOGITS
    楼ä¸ĭ
    0.28
    åľ¨éĤ£éĩĮ
    0.28
    notes
    0.27
     improv
    0.26
    çŁ¥æĥħ
    0.25
    çĶµæ°Ķ
    0.25
    decorators
    0.24
    esen
    0.24
     impunity
    0.24
    Çļ
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.