© 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. 23-TRANSCODER-HP
    7. 25093
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    0
    -0.30
    опеÑĢ
    -0.28
    1
    -0.27
    chaft
    -0.26
    äºĶä¸Ģ
    -0.26
    çĽĸ
    -0.25
    ```
    -0.25
    èĥ½
    -0.24
    èĵĭ
    -0.24
    getc
    -0.24
    POSITIVE LOGITS
    soever
    0.30
    isman
    0.30
    mue
    0.28
    aley
    0.27
    anton
    0.26
    PERT
    0.26
    iÄĩ
    0.25
    =?";↵
    0.25
    anmar
    0.25
     minimise
    0.25
    Activations Density 0.006%

    No Known Activations