© 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. 24734
    Prev
    Next
    INDEX
    Explanations

    $

    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
    empor
    -0.27
    ä¸ĩä¸Ģ
    -0.27
    uers
    -0.25
    è±ģ
    -0.24
    æŀ¶
    -0.24
    èĸĦ
    -0.24
    ä¸Ŀ毫
    -0.24
    htdocs
    -0.24
    uae
    -0.24
    æĤļ
    -0.24
    POSITIVE LOGITS
    chem
    0.35
     chrom
    0.28
     prot
    0.26
     timeframe
    0.25
    avy
    0.25
    che
    0.25
    دÙĪÙĨ
    0.25
     trait
    0.24
     range
    0.24
    aval
    0.24
    Activations Density 0.091%

    No Known Activations