© 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. 9090
    Prev
    Next
    INDEX
    Explanations

    Jonathan

    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
    èĥ¶
    -0.29
    å¹»
    -0.27
    ìłĦìŀIJ
    -0.26
     mult
    -0.26
     Parad
    -0.26
    SIGN
    -0.25
     gl
    -0.25
    anton
    -0.25
     glor
    -0.24
     multi
    -0.24
    POSITIVE LOGITS
    oader
    0.27
    åĴĦ
    0.27
    滩
    0.27
     "%.
    0.26
    ault
    0.25
    iets
    0.25
    éĶħ
    0.24
    izedName
    0.24
    ijľ
    0.24
    ãģĦãģij
    0.24
    Activations Density 0.950%

    No Known Activations