© 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. 57503
    Prev
    Next
    INDEX
    Explanations

    opioids/endorphins

    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
    åħļåĴĮ
    -0.32
    å§ij
    -0.26
    Annual
    -0.25
    å±¥
    -0.25
     каÑĩ
    -0.25
     deb
    -0.24
    éĩijéĻµ
    -0.24
    pod
    -0.24
    rail
    -0.24
    æīĭéĩĮ
    -0.24
    POSITIVE LOGITS
    åĶ¾
    0.28
     Morph
    0.25
     treated
    0.25
    æķijæ²»
    0.24
    &action
    0.24
    å¥ij约
    0.24
    æ²»
    0.23
     Ober
    0.23
    CardBody
    0.23
    _reservation
    0.23
    Activations Density 0.005%

    No Known Activations