© 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. 15-RESID-POST-AA
    11. 26569
    Prev
    Next
    INDEX
    Explanations

    abusive relationships

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    アウト
    -0.08
    ڼ
    -0.07
    ブル
    -0.07
    常态化
    -0.07
    鲽
    -0.07
    调整
    -0.06
    ($('<
    -0.06
    🐍
    -0.06
    🥀
    -0.06
    provided
    -0.06
    POSITIVE LOGITS
     Maria
    0.07
    jack
    0.07
     Cache
    0.06
    	sm
    0.06
     Bru
    0.06
     Neuro
    0.06
     Joh
    0.06
    ammu
    0.06
     Ai
    0.06
    	as
    0.06
    Activations Density 0.050%

    No Known Activations