© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 3161
    Prev
    Next
    INDEX
    Explanations

    tmp

    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
    posición
    -0.08
     Dani
    -0.08
     conv
    -0.07
    .schedule
    -0.07
    JsonIgnore
    -0.07
    剥夺
    -0.07
    presso
    -0.07
     '!
    -0.07
     يعتبر
    -0.07
     prov
    -0.07
    POSITIVE LOGITS
    крат
    0.07
     War
    0.07
     "↵
    0.07
     pit
    0.07
     empty
    0.06
    ود
    0.06
     Day
    0.06
    ድ
    0.06
    rh
    0.06
    '])↵
    0.06
    Activations Density 0.001%

    No Known Activations