© 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. 23821
    Prev
    Next
    INDEX
    Explanations

    colon

    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
    åħĪ导
    -0.29
    <center
    -0.26
    izador
    -0.26
    rollo
    -0.25
    еÑĨ
    -0.25
     ug
    -0.25
    iliate
    -0.24
    ä¹ĭä½ľ
    -0.24
    udit
    -0.24
    æ¯ĶåĪĨ
    -0.24
    POSITIVE LOGITS
     crow
    0.26
    uster
    0.26
     Counts
    0.24
    ä¸ļ
    0.24
    ارÙĬØ®
    0.24
    йÑĤи
    0.24
     Crow
    0.24
     snowy
    0.24
     Declaration
    0.23
    YY
    0.23
    Activations Density 0.004%

    No Known Activations