© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 86711
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    🐩
    -0.08
    ife
    -0.07
    Viewport
    -0.07
     air
    -0.06
    孩童
    -0.06
    .music
    -0.06
    Topology
    -0.06
    翠
    -0.06
    strument
    -0.06
    地质
    -0.06
    POSITIVE LOGITS
    其他玩家
    0.07
    衡阳
    0.07
     cmdline
    0.07
    ected
    0.07
     CB
    0.07
     cita
    0.07
    CustomAttributes
    0.07
     niezbędn
    0.06
    clamation
    0.06
     zamówienia
    0.06
    Activations Density 0.008%

    No Known Activations