© 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. 89925
    Prev
    Next
    INDEX
    Explanations

    1

    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
    מטוס
    -0.07
    _ON
    -0.07
    anoi
    -0.07
    随时
    -0.07
    资产负债
    -0.07
     Tibet
    -0.07
     maxLength
    -0.07
    <|im_end|>
    -0.07
     visc
    -0.07
     nulla
    -0.07
    POSITIVE LOGITS
    台
    0.07
    },{↵
    0.07
     Ironically
    0.07
    }}},↵
    0.07
     unfortunate
    0.07
    关
    0.07
     nominate
    0.06
    "`↵
    0.06
     Kernel
    0.06
    场
    0.06
    Activations Density 0.001%

    No Known Activations