© 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. 150140
    Prev
    Next
    INDEX
    Explanations

    The

    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
    ãn
    -0.29
     dict
    -0.29
     Charg
    -0.28
    dict
    -0.27
     charg
    -0.25
     Dictionary
    -0.25
     Wen
    -0.25
     Dict
    -0.24
    è½½
    -0.24
    çªģåĩ»
    -0.24
    POSITIVE LOGITS
    riendly
    0.27
    _ORIENTATION
    0.26
    å®ıè§Ĥ
    0.24
    ocale
    0.24
    .orientation
    0.24
    asiswa
    0.23
    æݨèĸ¦
    0.23
     Ãĺ
    0.23
    thalm
    0.23
    èģĶç³»æĸ¹å¼ı
    0.23
    Activations Density 0.886%

    No Known Activations