© 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. 23852
    Prev
    Next
    INDEX
    Explanations

    Mixed data sources

    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
    åºŀ
    -0.27
    -basket
    -0.27
     Panel
    -0.26
    éĿĻæĢģ
    -0.25
     afore
    -0.25
    åĽ½éĺ²éĥ¨
    -0.25
    Panel
    -0.25
    paper
    -0.25
    GUI
    -0.24
     getattr
    -0.24
    POSITIVE LOGITS
    ì°¨
    0.30
    Mate
    0.28
    æĺŁçIJĥ
    0.27
    reib
    0.26
     Uploaded
    0.25
    знаком
    0.25
    å¸IJ篷
    0.25
    ModelState
    0.24
    omial
    0.24
    ìļķ
    0.24
    Activations Density 0.000%

    No Known Activations