© 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. 23-TRANSCODER-HP
    7. 25210
    Prev
    Next
    INDEX
    Explanations

    research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Atoms
    -0.28
    olio
    -0.27
    ieder
    -0.26
     sniff
    -0.26
    OrNil
    -0.25
     Word
    -0.24
     Mixing
    -0.24
     yat
    -0.23
     dụ
    -0.23
     Points
    -0.23
    POSITIVE LOGITS
     categories
    0.59
    åĪĨåĮº
    0.57
     categor
    0.57
    åĪĴåĪĨ
    0.55
    ç»ĨåĪĨ
    0.54
    åĪĨç±»
    0.53
    categories
    0.52
     categorized
    0.50
    åĮºåĪĨ
    0.47
     differentiated
    0.47
    Activations Density 0.006%

    No Known Activations