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. 19-RESID-POST-AA
    6. 24350
    Prev
    Next
    INDEX
    Explanations

    earned

    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
     Addition
    -0.07
    luck
    -0.07
     unin
    -0.07
    砺
    -0.07
    Mrs
    -0.06
    Category
    -0.06
    ()?.
    -0.06
    申请人
    -0.06
    	Read
    -0.06
     Tân
    -0.06
    POSITIVE LOGITS
     söyled
    0.08
     RootState
    0.08
     smashing
    0.07
    SetText
    0.07
    .."
    0.07
     "#"
    0.07
    ftware
    0.07
     }),
    0.07
    ="#"
    0.06
    捍
    0.06
    Activations Density 0.013%

    No Known Activations