© 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. 9241
    Prev
    Next
    INDEX
    Explanations

    chemical formulas

    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
    综
    -0.28
     swung
    -0.26
    avar
    -0.26
     climbers
    -0.26
    éļIJèĶ½
    -0.25
    ahas
    -0.25
    åı¯è§ĨåĮĸ
    -0.24
     Clim
    -0.24
    ãģĹãģŁãĤĤãģ®
    -0.24
    ipi
    -0.24
    POSITIVE LOGITS
    UTO
    0.28
     contagious
    0.26
    é»İæĺİ
    0.25
    cem
    0.25
    emode
    0.25
    éĻĽ
    0.25
    ÑĤоп
    0.25
    SAMPLE
    0.25
    代çIJĨ
    0.24
    rig
    0.24
    Activations Density 0.090%

    No Known Activations