© 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. 95293
    Prev
    Next
    INDEX
    Explanations

    Software

    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
    sert
    -0.33
    rir
    -0.30
    ationToken
    -0.28
     exposing
    -0.27
    ukes
    -0.25
     plane
    -0.25
    åİ¿éķ¿
    -0.25
    é¤ħ
    -0.24
    éĭĨ
    -0.24
     expose
    -0.24
    POSITIVE LOGITS
     societies
    0.40
     society
    0.39
     Society
    0.37
     Soc
    0.31
     société
    0.29
     soc
    0.29
     Soci
    0.27
    社
    0.27
    feit
    0.26
    LatLng
    0.26
    Activations Density 0.889%

    No Known Activations