© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 122
    Prev
    Next
    INDEX
    Explanations

    LO

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æīij
    -0.27
    ahl
    -0.26
    å½ĵåľ°äºº
    -0.25
    iaux
    -0.25
    åĢ¼å®Ī
    -0.24
    ãĥĬãĥ¼
    -0.24
    éĻĤ
    -0.24
    Aligned
    -0.24
    orer
    -0.24
    ayette
    -0.23
    POSITIVE LOGITS
    èĢĮ
    0.26
    samp
    0.25
    ĵį
    0.25
    unny
    0.24
    ’an
    0.24
    esus
    0.24
    祯
    0.24
    å·¥ä½ľå®¤
    0.23
    mat
    0.23
     tand
    0.23
    Activations Density 0.007%

    No Known Activations