© 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. 22995
    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
    æĦ
    -0.27
    è¦ģæľī
    -0.27
    ::-
    -0.27
    жа
    -0.27
    vig
    -0.26
    æIJ
    -0.26
     inté
    -0.25
    èĴĪ
    -0.25
    çķ¥
    -0.24
    èĩªçĦ¶ä¿ĿæĬ¤
    -0.24
    POSITIVE LOGITS
    ksam
    0.29
     ÑĢÑĭ
    0.27
     Ryder
    0.26
    åīģ
    0.26
    TX
    0.26
    lor
    0.26
    >Lorem
    0.25
    ÙĪØ°
    0.24
    itivity
    0.24
     Whites
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.