© 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. 54086
    Prev
    Next
    INDEX
    Explanations

    philosophical/theoretical contexts

    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
    å±±èĦī
    -0.28
    天涯
    -0.27
    åįĥéĩĮ
    -0.26
    èµĦ
    -0.25
     GAL
    -0.25
    èĴ¸æ±½
    -0.24
    ringe
    -0.24
    æݬ
    -0.24
     elementary
    -0.24
    ç²Ĺç³Ļ
    -0.24
    POSITIVE LOGITS
     ground
    0.44
     Ground
    0.44
    ground
    0.42
    Ground
    0.39
    -ground
    0.34
    _ground
    0.32
     exp
    0.29
     convention
    0.28
     Vad
    0.28
    åħįç¨İ
    0.27
    Activations Density 0.042%

    No Known Activations