© 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. 57448
    Prev
    Next
    INDEX
    Explanations

    Psych

    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
    DOI
    -0.28
    åĽ½
    -0.28
    侧éĿ¢
    -0.27
    ä¸į容æĺĵ
    -0.27
    rig
    -0.27
    çħ§äº®
    -0.25
    ç»´
    -0.25
    容
    -0.24
     MPI
    -0.24
    éĢıè§Ĩ
    -0.24
    POSITIVE LOGITS
    usercontent
    0.28
    (controller
    0.27
     Psychiat
    0.27
    åŃ
    0.24
    æĥ³è±¡
    0.24
    èĬĻèĵī
    0.24
    æĦıè§ģåıįé¦Ī
    0.24
    é»ijé¾Ļ
    0.24
    -router
    0.24
    _FRIEND
    0.24
    Activations Density 0.001%

    No Known Activations