© 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
    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. 75753
    Prev
    Next
    INDEX
    Explanations

    Math word problems

    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
     merchants
    -0.08
     metal
    -0.07
    急性
    -0.07
     stranded
    -0.07
    心智
    -0.07
    趋势
    -0.07
     fossils
    -0.07
     Value
    -0.07
     �
    -0.06
    度过
    -0.06
    POSITIVE LOGITS
     yaml
    0.07
     anime
    0.07
     hum
    0.07
    首批
    0.07
    טעם
    0.07
    
    ↵
    
    ↵
    0.07
     feedback
    0.07
    违纪
    0.06
    𝘫
    0.06
     :'
    0.06
    Activations Density 0.010%

    No Known Activations