© 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. 8658
    Prev
    Next
    INDEX
    Explanations

    Foreign words

    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
     onFailure
    -0.28
     congr
    -0.25
    çĪĨ
    -0.24
     sense
    -0.24
    aku
    -0.24
    çľ¨çľ¼
    -0.24
    缸
    -0.24
    ÙĬÙģ
    -0.23
    Chance
    -0.23
    Multiplier
    -0.23
    POSITIVE LOGITS
    èĸĦèĨľ
    0.28
    ç®Ģæĺĵ
    0.27
    æŧ
    0.27
    itesse
    0.26
     hem
    0.26
    éªħ
    0.24
    ä¸ĵåijĺ
    0.24
     Hem
    0.24
    amin
    0.23
    chestra
    0.23
    Activations Density 0.007%

    No Known Activations