© 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. 32-TRANSCODER-HP
    7. 41275
    Prev
    Next
    INDEX
    Explanations

    level, Level variants

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    entes
    -0.26
    breaker
    -0.25
    è£ģåijĺ
    -0.25
     (<
    -0.25
    ervation
    -0.24
    bian
    -0.24
    ä¸Ĭç½ij
    -0.24
    å¼¹
    -0.24
    å¼
    -0.24
    esi
    -0.23
    POSITIVE LOGITS
     level
    1.20
    level
    1.05
     Level
    1.02
    _level
    0.98
     levels
    0.98
    Level
    0.94
     LEVEL
    0.94
    	level
    0.93
    -level
    0.91
    ãĥ¬ãĥĻãĥ«
    0.88
    Activations Density 0.003%

    No Known Activations