© 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. 149940
    Prev
    Next
    INDEX
    Explanations

    technical text

    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
    åŁºæķ°
    -0.27
    cup
    -0.25
     bound
    -0.25
     cup
    -0.24
    åīĮ
    -0.24
    åĪº
    -0.24
     ora
    -0.23
     CFG
    -0.23
     computer
    -0.23
     Council
    -0.23
    POSITIVE LOGITS
    åħĪ天
    0.28
    /theme
    0.27
     sexuality
    0.27
    éģĵ路交éĢļ
    0.27
    Themes
    0.27
    hydr
    0.26
    /xhtml
    0.26
     themes
    0.25
    rending
    0.25
    egot
    0.25
    Activations Density 0.952%

    No Known Activations