© 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. 108696
    Prev
    Next
    INDEX
    Explanations

    contractions using "not"

    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
    ä½ľä¸ºä¸Ģç§į
    -0.27
    ÄĻd
    -0.24
    è¾¹ç¼ĺ
    -0.24
    ahren
    -0.23
     attends
    -0.23
     microbi
    -0.23
    idency
    -0.23
     dimension
    -0.23
     Duty
    -0.23
    uls
    -0.23
    POSITIVE LOGITS
    .logical
    0.29
    plevel
    0.26
     discs
    0.25
    oma
    0.24
     stereotypes
    0.24
    à¸ĵะ
    0.24
    -talk
    0.24
    ÑĢев
    0.23
     stereotype
    0.23
    cha
    0.23
    Activations Density 0.294%

    No Known Activations