© 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. 24442
    Prev
    Next
    INDEX
    Explanations

    if

    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
     señ
    -0.29
    eous
    -0.28
    .compress
    -0.25
    éĵİ
    -0.25
    æ¶
    -0.25
    ë°ķ
    -0.24
    åĪļ
    -0.24
    loid
    -0.24
    StartPosition
    -0.24
    泪
    -0.24
    POSITIVE LOGITS
    顺åĪ©å®ĮæĪIJ
    0.39
    inde
    0.38
     continues
    0.34
     indeed
    0.34
     succeed
    0.32
     successful
    0.31
    åľĨ满å®ĮæĪIJ
    0.31
    å±ŀå®ŀ
    0.30
     Continue
    0.30
    继ç»Ńä¿ĿæĮģ
    0.29
    Activations Density 0.017%

    No Known Activations