© 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. 31-TRANSCODER-HP
    7. 18800
    Prev
    Next
    INDEX
    Explanations

    boat

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vern
    -0.29
    urm
    -0.28
    åķĨ
    -0.27
    èĴ¸
    -0.27
    èĥ¶
    -0.27
     maturity
    -0.26
    /*@
    -0.25
    åŁ¹
    -0.24
    orest
    -0.23
    çĽĺ
    -0.23
    POSITIVE LOGITS
    load
    0.34
     loaded
    0.32
    wright
    0.32
    è£ħè½½
    0.32
     unload
    0.32
     unloaded
    0.32
    loaded
    0.29
    -loader
    0.29
     Loader
    0.28
    -loading
    0.28
    Activations Density 1.086%

    No Known Activations