© 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. 75881
    Prev
    Next
    INDEX
    Explanations

    one, ones

    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
    �
    -0.08
     Stranger
    -0.07
    �
    -0.07
     surrender
    -0.07
    垓
    -0.07
    条件下
    -0.07
    banks
    -0.06
    Malloc
    -0.06
    芽
    -0.06
     sigh
    -0.06
    POSITIVE LOGITS
     Valent
    0.08
    èrent
    0.07
    	TR
    0.07
     Matte
    0.07
    仿
    0.07
     ومن
    0.07
     McInt
    0.07
    .getDefault
    0.07
     cooking
    0.07
    工作机制
    0.06
    Activations Density 0.025%

    No Known Activations