© 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. 107489
    Prev
    Next
    INDEX
    Explanations

    necessary

    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
    ois
    -0.28
    ä¸įä¸ĭ
    -0.25
    otes
    -0.25
    ote
    -0.24
    åı¯èĥ½æĢ§
    -0.24
    åĽ½æľī
    -0.24
    sville
    -0.23
    åĩĨæŶ
    -0.23
    -up
    -0.23
    auge
    -0.23
    POSITIVE LOGITS
    cop
    0.27
    mh
    0.26
     stop
    0.25
    ancock
    0.25
    tré
    0.25
     trag
    0.25
    hf
    0.25
    downloads
    0.25
    tt
    0.24
    ä¸įç®¡ä½ł
    0.24
    Activations Density 0.770%

    No Known Activations