© 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. 20-TRANSCODER-HP
    7. 107066
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elia
    -0.28
    ä¸Ģæŀ¶
    -0.26
    ведениÑı
    -0.26
    ä¸Ģ举
    -0.26
    ÑĩÑĮ
    -0.26
    bsites
    -0.26
    ocrin
    -0.24
     afterEach
    -0.24
    etine
    -0.24
    ãĥ§
    -0.24
    POSITIVE LOGITS
    atab
    0.32
    å°ī
    0.29
     imper
    0.28
    æ·ĺ
    0.28
    åıijè¾¾åĽ½å®¶
    0.28
     relevant
    0.26
    ub
    0.26
    ä»ħä»ħæĺ¯
    0.25
     Hale
    0.24
    åıĹå½±åĵį
    0.24
    Activations Density 22.823%

    No Known Activations

    This feature has no known activations.