© 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. 53266
    Prev
    Next
    INDEX
    Explanations

    change

    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
     GENERATED
    -0.27
    ÑĤелÑĮнÑĭе
    -0.27
    idebar
    -0.26
    imonials
    -0.26
    Compound
    -0.26
    åī¯
    -0.26
    äºĶ大
    -0.25
    Å©ng
    -0.25
    \Page
    -0.25
    orca
    -0.25
    POSITIVE LOGITS
    Change
    0.45
     Change
    0.44
     change
    0.42
    -change
    0.37
    F
    0.36
    change
    0.36
     changed
    0.34
    	change
    0.33
    W
    0.32
     CHANGE
    0.32
    Activations Density 0.015%

    No Known Activations