© 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. 24410
    Prev
    Next
    INDEX
    Explanations

    Abstract concepts

    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
    ä¿ĿæĮģçĿĢ
    -0.32
    ä¿ĿæĮģ
    -0.28
    å¿į
    -0.28
     зани
    -0.27
    ((__
    -0.27
     ignores
    -0.25
     Kub
    -0.25
    河边
    -0.25
     ignore
    -0.24
    ocache
    -0.24
    POSITIVE LOGITS
     via
    0.28
    adamente
    0.28
     wrong
    0.27
     differently
    0.26
     through
    0.26
    agh
    0.26
     headquartered
    0.25
     very
    0.25
    æ¦ľ
    0.25
     around
    0.24
    Activations Density 0.023%

    No Known Activations