© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RESID-POST-AA
    11. 86907
    Prev
    Next
    INDEX
    Explanations

    below

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .arm
    -0.08
    亲密
    -0.07
    贞
    -0.07
    แมน
    -0.07
     Watts
    -0.07
    荒
    -0.07
    .Data
    -0.06
    实习生
    -0.06
    าศ
    -0.06
    twór
    -0.06
    POSITIVE LOGITS
    	sub
    0.08
     bab
    0.07
     dismissing
    0.07
     derives
    0.07
    琀
    0.07
    	Buffer
    0.06
    	cont
    0.06
    	w
    0.06
     gerçek
    0.06
    .VERSION
    0.06
    Activations Density 0.062%

    No Known Activations