© 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. 107930
    Prev
    Next
    INDEX
    Explanations

    Jennifer

    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
    ettings
    -0.30
    ä¸Ŀ
    -0.28
    çĥĪ
    -0.27
    som
    -0.26
    anca
    -0.26
    åĩºåĽ½
    -0.25
    å¼¹
    -0.25
    åĹĵ
    -0.25
    æĺ¥
    -0.25
    frag
    -0.25
    POSITIVE LOGITS
    饩
    0.27
    ingly
    0.27
    plen
    0.26
    arium
    0.25
    FIXME
    0.24
    yll
    0.24
    TRL
    0.24
    ertain
    0.24
     bench
    0.23
     Indies
    0.23
    Activations Density 1.126%

    No Known Activations