© 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. 108848
    Prev
    Next
    INDEX
    Explanations

    planning and policy

    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
    zeich
    -0.28
    LAN
    -0.26
    panse
    -0.25
    çĨŁ
    -0.24
     pom
    -0.24
    ç»ĦåĽ¾
    -0.24
    -io
    -0.24
    Wed
    -0.24
    éĢĬ
    -0.24
     Pager
    -0.23
    POSITIVE LOGITS
    åľº
    0.27
     projects
    0.27
     policy
    0.26
    ãģĵãģ¨ãģĮãģĤãĤĬãģ¾ãģĻ
    0.26
     reforms
    0.26
     getField
    0.26
    atoon
    0.24
    good
    0.24
    é¡¹çĽ®å»ºè®¾
    0.24
     suffer
    0.23
    Activations Density 0.904%

    No Known Activations