© 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. 12-TRANSCODER-HP
    7. 23263
    Prev
    Next
    INDEX
    Explanations

    added to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edException
    -0.28
    è¶ħæłĩ
    -0.26
    次ä¼ļè®®
    -0.25
    ķĮ
    -0.25
    IFI
    -0.25
    èĩ³ä¸Ĭ
    -0.25
    uteur
    -0.24
    ä½į
    -0.24
    _hdl
    -0.24
     september
    -0.24
    POSITIVE LOGITS
    èĥĮ
    0.27
     sectors
    0.25
    InSection
    0.25
     presence
    0.25
    åīįåIJİ
    0.25
    ç»ŀ
    0.25
    ôt
    0.25
    alette
    0.24
    .ini
    0.24
    Ы
    0.24
    Activations Density 0.002%

    No Known Activations