© 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. 56970
    Prev
    Next
    INDEX
    Explanations

    academic studies

    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
    温
    -0.28
    å½ĵæĹ¥
    -0.27
    è¿ĻæĶ¯
    -0.26
    èħ¥
    -0.26
    çĥŃæ½®
    -0.26
    æīĭèĦļ
    -0.25
     laat
    -0.25
    æļĸ
    -0.24
    å½ĵ天
    -0.24
    éĶ¦æłĩ
    -0.24
    POSITIVE LOGITS
    obbies
    0.31
    ocio
    0.31
     baseline
    0.31
     location
    0.30
     independence
    0.29
     negativity
    0.28
     observation
    0.28
    aseline
    0.27
    ademic
    0.27
    otype
    0.27
    Activations Density 0.022%

    No Known Activations