© 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. 69599
    Prev
    Next
    INDEX
    Explanations

    say "else" and "form"

    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
     Mars
    -0.08
     moral
    -0.07
    妲
    -0.07
     CONNECT
    -0.07
    Multiplicity
    -0.07
     presents
    -0.07
     Publish
    -0.07
     מוצרים
    -0.07
    ambia
    -0.07
     discussed
    -0.06
    POSITIVE LOGITS
    均衡
    0.08
    -gr
    0.07
    烘
    0.07
     sx
    0.07
     attackers
    0.07
    讳
    0.07
    getSession
    0.07
    であ
    0.07
     smaller
    0.07
    .slice
    0.07
    Activations Density 0.002%

    No Known Activations