© 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. 6362
    Prev
    Next
    INDEX
    Explanations

    Code with labels

    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
    need
    -0.08
     Within
    -0.07
    邱
    -0.07
     torture
    -0.07
     upon
    -0.07
    Cfg
    -0.07
    inf
    -0.07
     causes
    -0.07
    钱
    -0.07
    עם
    -0.07
    POSITIVE LOGITS
    🎳
    0.07
     Shi
    0.07
     Veter
    0.07
    производ
    0.07
    (Sprite
    0.06
    腥
    0.06
    _actor
    0.06
     CONNECTION
    0.06
    redi
    0.06
     сохрани
    0.06
    Activations Density 0.018%

    No Known Activations