© 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. 107748
    Prev
    Next
    INDEX
    Explanations

    from

    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
    她
    -0.27
    à¤
    -0.25
    -Sep
    -0.25
    決ãĤģ
    -0.25
    enschaft
    -0.24
    åĨ³å®ļ
    -0.24
    ä¼łç»Łäº§ä¸ļ
    -0.24
    everything
    -0.24
    åĽĽå¹´
    -0.24
    ide
    -0.24
    POSITIVE LOGITS
    esub
    0.31
     Associated
    0.25
    oins
    0.25
    [email
    0.25
     Directions
    0.25
    æ¶
    0.25
    лаÑģÑĤ
    0.24
    DataTask
    0.24
    .getLogger
    0.24
    orneys
    0.24
    Activations Density 0.926%

    No Known Activations