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. 2937
    Prev
    Next
    INDEX
    Explanations

    something being attached

    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
    -provider
    -0.07
    スポー�
    -0.07
    /arch
    -0.06
    .backend
    -0.06
    �
    -0.06
    人々
    -0.06
    짧
    -0.06
     �
    -0.06
     النظام
    -0.06
    ANDARD
    -0.06
    POSITIVE LOGITS
    xB
    0.08
    ام
    0.08
    Is
    0.07
    ']]↵
    0.07
    ibal
    0.07
     proceeded
    0.07
    ана
    0.06
     RPM
    0.06
    Saga
    0.06
    atos
    0.06
    Activations Density 0.014%

    No Known Activations