© 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. 107538
    Prev
    Next
    INDEX
    Explanations

    gibberish

    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
     Raid
    -0.27
     Treaty
    -0.27
    dig
    -0.26
    mates
    -0.26
    å¤ĩ
    -0.25
     Needle
    -0.25
    æ£ķèī²
    -0.24
    ä¸ŃåĽ½å¸Ĥåľº
    -0.24
    åĢĴ
    -0.24
    éĥģ
    -0.24
    POSITIVE LOGITS
     recruitment
    0.30
    abis
    0.29
    orian
    0.26
    ç±į
    0.25
     cleric
    0.25
    çľģå¸Ĥ
    0.25
    èģļéĽĨ
    0.25
    åıĤä¸İåĪ°
    0.24
     recruited
    0.24
    æĭĽæĶ¶
    0.24
    Activations Density 1.121%

    No Known Activations