© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 33-TRANSCODER-HP
    7. 54644
    Prev
    Next
    INDEX
    Explanations

    to

    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
    Negative Logits
     double
    -0.58
     Double
    -0.50
    Double
    -0.47
    double
    -0.46
    åıĮ
    -0.46
    _double
    -0.42
    .Double
    -0.39
    	Double
    -0.39
    	double
    -0.38
     DOUBLE
    -0.37
    POSITIVE LOGITS
    Behind
    0.27
    ilate
    0.27
    æį¢å±Ĭ
    0.26
    pora
    0.26
    emale
    0.25
    ÑĢаÑī
    0.25
    fern
    0.25
    rove
    0.24
    åıijå±ķ缮æłĩ
    0.24
    reet
    0.24
    Activations Density 0.010%

    No Known Activations