© 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. 9-TRANSCODER-HP
    7. 30084
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .done
    -0.28
    ten
    -0.26
     [[]
    -0.26
    >{!!
    -0.25
    æĬĺåıł
    -0.25
    è¿Ļä¹Īåģļ
    -0.25
     emacs
    -0.25
     django
    -0.24
    æ¯Ķè¼ĥ
    -0.24
    .fromString
    -0.24
    POSITIVE LOGITS
    raud
    0.25
    inium
    0.25
    ingleton
    0.24
    æ±Łå±±
    0.24
    #__
    0.24
    @js
    0.23
    çģ«çĦ°
    0.23
    appropriate
    0.23
    Morning
    0.23
    pection
    0.23
    Activations Density 41.655%

    No Known Activations