© 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. 41013
    Prev
    Next
    INDEX
    Explanations

    Weight/Size

    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
    ä¸įåIJĮ
    -0.28
    ائ
    -0.26
     KN
    -0.26
     sideways
    -0.26
     sources
    -0.26
    aval
    -0.25
     anywhere
    -0.25
     Sources
    -0.25
    ages
    -0.25
     treatment
    -0.24
    POSITIVE LOGITS
     disemb
    0.28
    ahkan
    0.28
    \Active
    0.26
     ease
    0.25
     proposition
    0.25
    æĬ
    0.25
    ulator
    0.25
    çļĦéľĢæ±Ĥ
    0.25
    servername
    0.25
     Moderator
    0.24
    Activations Density 0.819%

    No Known Activations