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. 44212
    Prev
    Next
    INDEX
    Explanations

    mi

    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
     retired
    -0.07
     Peoples
    -0.07
    Override
    -0.07
    قود
    -0.07
     ENTRY
    -0.07
     biomass
    -0.07
     De
    -0.07
    诮
    -0.07
    嫚
    -0.07
     עומד
    -0.07
    POSITIVE LOGITS
    实景
    0.08
    water
    0.07
     dotyc
    0.07
    뀜
    0.07
    cratch
    0.07
    izu
    0.07
    מנהיג
    0.07
    \models
    0.07
    téri
    0.07
    represent
    0.07
    Activations Density 0.004%

    No Known Activations