© 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. 109321
    Prev
    Next
    INDEX
    Explanations

    time period in months/years

    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
     withholding
    -0.08
    \Dependency
    -0.08
    ValueHandling
    -0.07
    什么事
    -0.07
    箕
    -0.07
     Jungle
    -0.07
    火烧
    -0.07
    ści
    -0.07
     Georgian
    -0.07
    对不起
    -0.07
    POSITIVE LOGITS
    [f
    0.07
    getConnection
    0.07
    ꡔ
    0.07
     fixes
    0.07
    (best
    0.07
    ให
    0.07
    .create
    0.07
    排查
    0.06
    交通枢纽
    0.06
    [q
    0.06
    Activations Density 0.048%

    No Known Activations