© 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. 108081
    Prev
    Next
    INDEX
    Explanations

    :

    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
     translate
    -0.27
    translate
    -0.27
     lan
    -0.26
     shield
    -0.26
    èļģ
    -0.25
    ind
    -0.25
     depart
    -0.25
     lib
    -0.25
    }|
    -0.25
     starting
    -0.24
    POSITIVE LOGITS
     Cust
    0.27
    паÑĢ
    0.26
    .GetBytes
    0.25
    utral
    0.25
    tour
    0.24
    æIJŀ好
    0.24
    çłĤæµĨ
    0.24
    eprom
    0.24
    BODY
    0.23
    arcy
    0.23
    Activations Density 0.274%

    No Known Activations