© 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. 107412
    Prev
    Next
    INDEX
    Explanations

    Specific or varied contexts

    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
    å¤ļä½Ļ
    -0.26
    å½ĵåīįä½įç½®
    -0.26
    éĥ¨éŨ
    -0.26
     basis
    -0.25
    ÙĦÙĥ
    -0.25
    称
    -0.25
    stit
    -0.25
    åĵªäºĽ
    -0.25
    ç¾İ好çļĦ
    -0.25
    å¤ļä½ĻçļĦ
    -0.25
    POSITIVE LOGITS
     divorced
    0.31
    ä¸įæľį
    0.30
     adjoining
    0.28
     Returned
    0.27
    èĢĮéĿŀ
    0.27
     Spears
    0.26
    å¾Īåı¯èĥ½
    0.26
    ValidationError
    0.25
    _validator
    0.25
     returned
    0.25
    Activations Density 0.901%

    No Known Activations