© 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. 19-TRANSCODER-HP
    7. 8465
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thus
    -0.27
     reopen
    -0.26
    apis
    -0.25
     vid
    -0.25
    s
    -0.25
    Gs
    -0.24
    EVER
    -0.24
    reopen
    -0.24
     commerc
    -0.24
    enter
    -0.24
    POSITIVE LOGITS
    æŀľ
    0.34
     inconsistency
    0.28
    æķ£
    0.28
     inconsistent
    0.28
    ioned
    0.27
    è¿«
    0.25
    æ¯ħåĬĽ
    0.24
     unacceptable
    0.24
    èįij
    0.24
    ä¸Ģçľĭ
    0.23
    Activations Density 1.675%

    No Known Activations

    This feature has no known activations.