© 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. 22-TRANSCODER-HP
    7. 129765
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alous
    -0.25
     Tay
    -0.25
    .After
    -0.24
    .gg
    -0.24
    orro
    -0.24
    åĽ½å®¶éĩįçĤ¹
    -0.24
     affirmative
    -0.24
     indefinitely
    -0.23
     Pty
    -0.23
    OAD
    -0.23
    POSITIVE LOGITS
    秩
    0.27
    éĻ©
    0.26
     impulse
    0.25
     sin
    0.25
     XB
    0.25
    ç¨ĭ度
    0.24
    hood
    0.24
    umbs
    0.23
    ping
    0.23
    éĤ£åıª
    0.23
    Activations Density 0.007%

    No Known Activations

    This feature has no known activations.