© 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. 22553
    Prev
    Next
    INDEX
    Explanations

    Recommending locations

    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
    blem
    -0.28
    uben
    -0.27
    Won
    -0.26
     DEAL
    -0.26
    /demo
    -0.25
    +","+
    -0.25
    .ids
    -0.25
    Ñıми
    -0.25
    testdata
    -0.24
    ноÑģÑĤ
    -0.24
    POSITIVE LOGITS
    å½ĵæŶ
    0.32
    å½ĵæŶçļĦ
    0.30
    èł
    0.26
     navigate
    0.25
     option
    0.25
     appeal
    0.25
    幸
    0.24
     avoided
    0.24
    ä¸Ģåįĥ
    0.24
     è
    0.24
    Activations Density 0.001%

    No Known Activations