© 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. 108181
    Prev
    Next
    INDEX
    Explanations

    ath

    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
     Perm
    -0.29
    ä¸ij
    -0.28
    å¸Ī
    -0.27
     perms
    -0.27
    ÑģÑĤÑĢ
    -0.26
    Presentation
    -0.25
    ÑģÑĤÑĢел
    -0.25
    stre
    -0.24
    åĪĹ为
    -0.24
    åĬĽäºī
    -0.24
    POSITIVE LOGITS
    omas
    0.31
    ér
    0.29
    erton
    0.28
    ä¼łè¯´
    0.27
    abile
    0.26
    |=↵
    0.25
    ousand
    0.25
    letes
    0.25
    roid
    0.24
    orst
    0.24
    Activations Density 1.335%

    No Known Activations