© 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. 108365
    Prev
    Next
    INDEX
    Explanations

    Given

    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
     keeps
    -0.25
    è´¸æĺĵ
    -0.24
    ber
    -0.24
    Ham
    -0.24
    беÑĢ
    -0.23
    Ñīа
    -0.23
    _Tool
    -0.23
    untos
    -0.23
    Be
    -0.23
     Ham
    -0.23
    POSITIVE LOGITS
    |RF
    0.36
    Its
    0.28
    ä¸ĭ称
    0.27
    åįģ足
    0.27
    %x
    0.27
     its
    0.26
    åħ¶
    0.25
    -valid
    0.25
    MASK
    0.25
    XR
    0.25
    Activations Density 0.160%

    No Known Activations