© 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. 12-TRANSCODER-HP
    7. 22977
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Confirmation
    -0.26
     pard
    -0.24
    -dir
    -0.24
     ÑģоÑħ
    -0.24
    èĬ±çĵ£
    -0.24
     Forg
    -0.23
     dilig
    -0.23
    .responses
    -0.23
    æħij
    -0.23
    Confirmation
    -0.23
    POSITIVE LOGITS
    anian
    0.29
    ÃľN
    0.27
    èĩ£
    0.26
    aż
    0.26
    sı
    0.25
    å®ĺ
    0.25
     faces
    0.24
    xffffffff
    0.24
    ác
    0.24
    åĬ¨åijĺ
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.