© 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. 42840
    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
    ness
    -0.27
    å¯¹æľªæĿ¥
    -0.24
     bik
    -0.23
     UPC
    -0.23
     ingestion
    -0.22
     Burk
    -0.22
    åħ·ä½ĵæĥħåĨµ
    -0.22
    berger
    -0.21
    scoped
    -0.21
     borderline
    -0.21
    POSITIVE LOGITS
     Ruf
    0.26
    /AFP
    0.24
    .sel
    0.24
    .toByteArray
    0.24
    湿润
    0.23
    nage
    0.23
    ][-
    0.23
    庶
    0.23
    ombo
    0.23
    AAF
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.