© 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. 108515
    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
    gl
    -0.28
    å¹´å¼Ģå§ĭ
    -0.28
    ι
    -0.26
     gl
    -0.25
    mith
    -0.25
    loom
    -0.25
    年第
    -0.24
    -config
    -0.24
    .End
    -0.24
    .gl
    -0.24
    POSITIVE LOGITS
    ieres
    0.27
    ARDS
    0.27
     Feinstein
    0.26
    çĦ¶æĺ¯
    0.26
     feasibility
    0.26
    tant
    0.26
    ussions
    0.26
    uhl
    0.25
    amel
    0.24
     Grave
    0.23
    Activations Density 1.944%

    No Known Activations