© 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. 25-TRANSCODER-HP
    7. 107763
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sockaddr
    -0.25
    icted
    -0.25
    å±ħ室
    -0.24
     fires
    -0.24
    igator
    -0.23
    enberg
    -0.23
    åħįéĻ¤
    -0.23
    azar
    -0.23
     zeros
    -0.23
     dri
    -0.22
    POSITIVE LOGITS
    ť
    0.28
    age
    0.27
    yne
    0.27
    è¿Ľä¸ĢæŃ¥
    0.26
    UNK
    0.25
     White
    0.24
    White
    0.24
     collo
    0.24
    对æѤ
    0.23
    à¹Ģà¸Īà¸Ń
    0.23
    Activations Density 0.129%

    No Known Activations