© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 57299
    Prev
    Next
    INDEX
    Explanations

    scallops

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SIG
    -0.07
     помог
    -0.07
    indered
    -0.07
     hated
    -0.07
    orton
    -0.07
    /reset
    -0.07
    _consts
    -0.07
    rules
    -0.07
    授
    -0.07
     vir
    -0.07
    POSITIVE LOGITS
    .plan
    0.07
    ,c
    0.06
    运费
    0.06
    Utilities
    0.06
    彳
    0.06
    е�
    0.06
    🏚
    0.06
    íf
    0.06
    电子产品
    0.06
    �
    0.06
    Activations Density 0.001%

    No Known Activations