© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 75452
    Prev
    Next
    INDEX
    Explanations

    Duration prepositions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    關鍵
    -0.07
     sins
    -0.07
    Stephen
    -0.07
    Iron
    -0.07
     Cooling
    -0.07
     fallen
    -0.07
    汴
    -0.07
    坦言
    -0.07
     Rav
    -0.07
     division
    -0.07
    POSITIVE LOGITS
     Disco
    0.07
    ⋋
    0.07
    җ
    0.07
    盘
    0.06
     accus
    0.06
     interv
    0.06
    interested
    0.06
    巡逻
    0.06
    твор
    0.06
     Opr
    0.06
    Activations Density 0.041%

    No Known Activations