© 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. 30-TRANSCODER-HP
    7. 95808
    Prev
    Next
    INDEX
    Explanations

    special

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pread
    -0.25
    ACH
    -0.25
     depos
    -0.25
    èĴĮ
    -0.24
    avi
    -0.24
     apolog
    -0.24
    aping
    -0.24
     favor
    -0.24
     her
    -0.24
    olor
    -0.24
    POSITIVE LOGITS
    izable
    0.33
    ising
    0.29
     Programme
    0.28
    isiert
    0.28
    izations
    0.28
    ized
    0.28
    isation
    0.28
    ç»Ħç»ĩå®ŀæĸ½
    0.27
    acas
    0.27
    ization
    0.27
    Activations Density 0.108%

    No Known Activations