© 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. 30-TRANSCODER-HP
    7. 96411
    Prev
    Next
    INDEX
    Explanations

    ana

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    owl
    -0.26
    Ñıз
    -0.25
    ç¯Ģ
    -0.25
     PROGMEM
    -0.24
    çijŁ
    -0.24
    institution
    -0.24
     subtree
    -0.24
    (EFFECT
    -0.24
     keyboard
    -0.24
    å¹»
    -0.24
    POSITIVE LOGITS
     ana
    0.76
    ana
    0.66
     Ana
    0.62
    åİĮ
    0.54
    Ana
    0.53
     land
    0.48
    å¡«
    0.46
     Land
    0.45
    åİŃ
    0.45
    ANA
    0.44
    Activations Density 0.991%

    No Known Activations