© 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. 23-TRANSCODER-HP
    7. 24558
    Prev
    Next
    INDEX
    Explanations

    technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FieldType
    -0.27
     type
    -0.27
    ourney
    -0.27
    EventType
    -0.26
    Categories
    -0.26
    mlin
    -0.26
    ä¸¥æł¼æī§è¡Į
    -0.26
    ä¸¥æł¼æĮīçħ§
    -0.26
    Cop
    -0.25
     abuse
    -0.25
    POSITIVE LOGITS
    angling
    0.30
    zac
    0.28
     Gim
    0.26
    xCF
    0.24
    åŃĹåı·
    0.24
     sleeper
    0.24
    ISR
    0.24
     EMC
    0.23
    _mes
    0.23
     anz
    0.23
    Activations Density 0.000%

    No Known Activations