© 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. 9910
    Prev
    Next
    INDEX
    Explanations

    berry/orm

    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
     Whilst
    -0.07
     solitude
    -0.07
     luxury
    -0.07
    安定
    -0.07
    ?type
    -0.06
    agner
    -0.06
    */,
    -0.06
    _videos
    -0.06
    _reservation
    -0.06
    失效
    -0.06
    POSITIVE LOGITS
    内置
    0.07
     recogn
    0.07
     [|
    0.07
    Kernel
    0.07
    smarty
    0.07
    leich
    0.07
    eatures
    0.07
     EEPROM
    0.07
     forth
    0.07
     לפי
    0.07
    Activations Density 0.001%

    No Known Activations