© 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. 7-RESID-POST-AA
    11. 76434
    Prev
    Next
    INDEX
    Explanations

    ium

    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
    Directed
    -0.07
    还算
    -0.07
    时光
    -0.06
     alright
    -0.06
    venida
    -0.06
    _COD
    -0.06
    iriş
    -0.06
     ::
    -0.06
    웰
    -0.06
    캇
    -0.06
    POSITIVE LOGITS
     europé
    0.07
     anim
    0.07
    —we
    0.07
    imu
    0.07
    .Office
    0.07
     стоим
    0.07
     pagan
    0.07
     myster
    0.07
    被人
    0.07
     Unix
    0.07
    Activations Density 0.001%

    No Known Activations