© 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. 27-TRANSCODER-HP
    7. 57092
    Prev
    Next
    INDEX
    Explanations

    aid

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     поб
    -0.25
    交éĢļå·¥åħ·
    -0.25
    ÑĢажа
    -0.24
    大家åĪĨ享
    -0.24
    owi
    -0.24
    æµ®åĬ¨
    -0.24
    unda
    -0.24
    èĦ¸èī²
    -0.23
    alic
    -0.23
    gorithm
    -0.23
    POSITIVE LOGITS
    ÂŃi
    0.25
    å¹´éĻIJ
    0.25
    stone
    0.24
     superior
    0.24
     chop
    0.24
     solidity
    0.23
    ç»Ń约
    0.23
    ele
    0.23
    åĪ¶
    0.23
    apl
    0.23
    Activations Density 0.990%

    No Known Activations