© 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. 22867
    Prev
    Next
    INDEX
    Explanations

    rosis

    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
    æ³°å±±
    -0.27
    UF
    -0.27
    “He
    -0.26
    ierge
    -0.26
     Exception
    -0.26
    BS
    -0.25
    ÑĮе
    -0.24
    ண
    -0.24
     UF
    -0.24
    izi
    -0.24
    POSITIVE LOGITS
    å°ıæŶåīį
    0.31
    alon
    0.28
    .FLAG
    0.27
    kaar
    0.27
    semblies
    0.27
    èįī
    0.25
    _sv
    0.24
    emics
    0.24
     }),↵↵
    0.24
    zyst
    0.23
    Activations Density 0.004%

    No Known Activations