© 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. 33-TRANSCODER-HP
    7. 53778
    Prev
    Next
    INDEX
    Explanations

    safety measures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĩĩåıĸ
    -1.01
    æİ¡åıĸ
    -0.83
    æݪæĸ½
    -0.71
    举æݪ
    -0.60
     measures
    -0.58
     Measures
    -0.56
     measure
    -0.50
    éĩįè¦ģ举æݪ
    -0.39
     Measure
    -0.34
     Take
    -0.32
    POSITIVE LOGITS
     æİ
    0.47
     me
    0.46
    me
    0.44
     Me
    0.43
     Ma
    0.42
     meas
    0.41
    Me
    0.41
    	Me
    0.39
    Ma
    0.38
    _me
    0.37
    Activations Density 0.108%

    No Known Activations