© 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. 43402
    Prev
    Next
    INDEX
    Explanations

    with

    np_max-act-logits · gemini-2.0-flash
    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
    rather
    -0.28
    endent
    -0.27
    çijŁ
    -0.27
    è¿ĽåĨĽ
    -0.27
    owitz
    -0.27
     rather
    -0.26
    .filePath
    -0.24
    uis
    -0.24
     suất
    -0.24
    enting
    -0.24
    POSITIVE LOGITS
     distinction
    0.34
    å¥ĩ
    0.34
     complexity
    0.32
     uniqueness
    0.32
     focus
    0.32
     transparency
    0.31
     clarity
    0.30
    çĭIJ
    0.30
     authenticity
    0.30
    çĽĺ
    0.30
    Activations Density 0.002%

    No Known Activations