© 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. 24-TRANSCODER-HP
    7. 150493
    Prev
    Next
    INDEX
    Explanations

    technical writing snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åħ¶ä»ĸ
    -0.34
    åħ¶ä»ĸåĽ½å®¶
    -0.28
     (~
    -0.27
     MyBase
    -0.26
    sim
    -0.26
    诸å¦Ĥ
    -0.26
    æ®Ľ
    -0.26
    éĻĩ
    -0.25
     Lands
    -0.24
     circa
    -0.24
    POSITIVE LOGITS
    acf
    0.27
    ERV
    0.27
    arov
    0.26
    aryl
    0.25
    ])]
    0.25
    .Xr
    0.25
    "),"
    0.25
    azed
    0.25
    encies
    0.25
    CHAT
    0.24
    Activations Density 1.056%

    No Known Activations