© 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. 58119
    Prev
    Next
    INDEX
    Explanations

    Emotional

    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
     collabor
    -0.37
     partnership
    -0.36
    å¥ij约
    -0.33
     collaboration
    -0.32
     Collabor
    -0.31
     collaborating
    -0.30
    íķĻêµIJ
    -0.30
     partnerships
    -0.30
     Partnership
    -0.29
     collaborate
    -0.29
    POSITIVE LOGITS
    _STACK
    0.26
     diret
    0.26
     istediÄŁi
    0.26
    ä¸įå¾Ĺ
    0.24
    åıij表
    0.24
    ]').
    0.23
    çŃĶé¢ĺ
    0.23
    è¿ĩäºĨ
    0.23
     prose
    0.23
     долж
    0.23
    Activations Density 0.002%

    No Known Activations