Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 87124
    Prev
    Next
    INDEX
    Explanations

    Foreign language

    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
     pact
    -0.07
    发生变化
    -0.07
     household
    -0.07
    𝐛
    -0.07
     Invoice
    -0.07
    included
    -0.07
     decision
    -0.06
    脎
    -0.06
    Province
    -0.06
    riangle
    -0.06
    POSITIVE LOGITS
    ,
    0.11
    	  	
    0.08
    惰
    0.08
    流水
    0.07
    .CON
    0.07
    是可以
    0.07
    yclic
    0.07
    Numer
    0.07
     Pont
    0.07
     أجل
    0.07
    Activations Density 0.090%

    No Known Activations