© 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. 150233
    Prev
    Next
    INDEX
    Explanations

    very

    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
     pur
    -0.29
    -module
    -0.27
    führung
    -0.26
     "--
    -0.25
    mong
    -0.25
    rollo
    -0.25
    çĶŁçĶŁ
    -0.24
    箫
    -0.24
     Almost
    -0.24
    ба
    -0.24
    POSITIVE LOGITS
    å®Įç¾İçļĦ
    0.30
    éĹ³
    0.29
     tolerant
    0.26
    Uvs
    0.26
    endid
    0.25
    _CONSOLE
    0.25
    åģ¥åº·çļĦ
    0.24
    å®Įç¾İ
    0.24
    TimeInterval
    0.24
    ŃIJ
    0.24
    Activations Density 0.221%

    No Known Activations