© 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. 14-TRANSCODER-HP
    7. 40955
    Prev
    Next
    INDEX
    Explanations

    Vikings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -toggler
    -0.28
    unities
    -0.27
     strengths
    -0.25
    çĶµè´¹
    -0.24
    Ĥ¨
    -0.24
    çĪ±ä½ł
    -0.24
     floats
    -0.24
    ÃŃm
    -0.24
    кли
    -0.23
     WebClient
    -0.23
    POSITIVE LOGITS
    çļĦåĵģçīĮ
    0.35
    jet
    0.32
    ora
    0.31
    amento
    0.28
    ä¾ĽåĽ¾
    0.28
    ero
    0.28
    DAT
    0.27
     cul
    0.27
    rance
    0.27
    amenti
    0.26
    Activations Density 0.859%

    No Known Activations