© 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. 108485
    Prev
    Next
    INDEX
    Explanations

    Code/Licensing documentation

    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
     heading
    -0.25
     concerned
    -0.24
    Owner
    -0.24
    aries
    -0.24
     passer
    -0.24
    åİŁæĸĩåľ°åĿĢ
    -0.24
    .assertNot
    -0.23
     ocup
    -0.23
    æıIJåĪ°
    -0.23
     shrink
    -0.23
    POSITIVE LOGITS
    ivec
    0.31
    æĿµ
    0.30
     Wahl
    0.28
    æ¥Ķ
    0.27
    ä¸İä¼Ĺ
    0.26
     Strange
    0.26
    滥
    0.25
    Strange
    0.25
    æľĪä¸ĭ
    0.25
    й
    0.25
    Activations Density 0.062%

    No Known Activations