© 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. 19-RESID-POST-AA
    6. 68624
    Prev
    Next
    INDEX
    Explanations

    hometown

    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
    TE
    -0.08
    ﺍ
    -0.07
    opo
    -0.07
     가운데
    -0.07
     thee
    -0.07
    /DTD
    -0.07
    ptune
    -0.06
    事实上
    -0.06
    zed
    -0.06
    贵族
    -0.06
    POSITIVE LOGITS
    มาก
    0.07
    .Dom
    0.07
    ackson
    0.07
    totals
    0.07
    .Property
    0.07
     disappointment
    0.07
     dần
    0.07
    	Local
    0.07
    squ
    0.06
    ┘
    0.06
    Activations Density 0.020%

    No Known Activations