© 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. 23723
    Prev
    Next
    INDEX
    Explanations

    General text and conversations

    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
     ör
    -0.26
    csr
    -0.25
     csr
    -0.24
     munch
    -0.24
     dara
    -0.23
    ÑĪин
    -0.23
     agreed
    -0.23
    rift
    -0.23
    .MustCompile
    -0.23
     <<<
    -0.23
    POSITIVE LOGITS
    enced
    0.29
    .PR
    0.24
    çĦĵ
    0.24
    ificados
    0.24
    DataManager
    0.24
    å®ļäºĨ
    0.24
    intl
    0.23
     Sw
    0.23
    æ²¹èĦĤ
    0.23
    aux
    0.23
    Activations Density 0.001%

    No Known Activations