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. 15-RESID-POST-AA
    6. 16656
    Prev
    Next
    INDEX
    Explanations

    important

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.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
     очередь
    -0.07
     gluten
    -0.07
     llev
    -0.07
    sock
    -0.07
     xương
    -0.07
    Nut
    -0.07
    nea
    -0.07
    ceive
    -0.06
    今回は
    -0.06
    POSITIVE LOGITS
     whit
    0.08
     Memorial
    0.07
    יפים
    0.07
     inventions
    0.07
     mục
    0.06
    umbnail
    0.06
     familiar
    0.06
    Paths
    0.06
     מקבל
    0.06
     retains
    0.06
    Activations Density 0.018%

    No Known Activations