© 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. 109169
    Prev
    Next
    INDEX
    Explanations

    dom/dum

    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
     identities
    -0.28
     Follow
    -0.28
    erals
    -0.26
    ENCIL
    -0.26
    e
    -0.26
    utions
    -0.26
    ÑģÑĤи
    -0.25
     placer
    -0.24
    ä¸Ģä¸ĭ
    -0.24
    ìĦĿ
    -0.24
    POSITIVE LOGITS
    ÂŃi
    0.28
    æĸ°éĹ»è®°èĢħ
    0.26
    好åĿı
    0.26
    ingly
    0.25
    æľĢ好
    0.25
    ĪæĿĥ
    0.25
    pig
    0.24
    Ni
    0.24
    åıijçĹħçİĩ
    0.24
    *math
    0.24
    Activations Density 0.069%

    No Known Activations