© 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. 96000
    Prev
    Next
    INDEX
    Explanations

    animals

    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
    ä¸ĢåŃĹ
    -0.30
    ór
    -0.28
    èĵ£
    -0.27
    奥æŀĹ
    -0.26
    æĩĭ
    -0.25
    çĽĶ
    -0.24
    Evaluator
    -0.23
    人åĬĽ
    -0.23
    Player
    -0.23
    ahi
    -0.23
    POSITIVE LOGITS
     cats
    1.06
    çĮ«
    1.02
     dogs
    0.98
    çĭĹ
    0.92
     cat
    0.91
     animals
    0.90
     dog
    0.86
     rats
    0.86
    çĬ¬
    0.85
     mice
    0.84
    Activations Density 1.577%

    No Known Activations