© 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. 30-TRANSCODER-HP
    7. 95762
    Prev
    Next
    INDEX
    Explanations

    Explaining, describing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¼ļ被
    -0.29
    åıĪ被
    -0.28
    roof
    -0.28
    åį³ä½¿
    -0.27
    imir
    -0.26
    è¿«
    -0.25
    YRO
    -0.25
    even
    -0.25
    å±ŀäºİèĩªå·±
    -0.24
    umble
    -0.24
    POSITIVE LOGITS
     explain
    0.44
     describe
    0.43
     reference
    0.42
     explains
    0.41
    æııè¿°
    0.40
     explaining
    0.40
    éĺIJè¿°
    0.39
     referencing
    0.38
     reflect
    0.38
     refer
    0.37
    Activations Density 0.894%

    No Known Activations