© 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. 80183
    Prev
    Next
    INDEX
    Explanations

    endian or ether

    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
    钣
    -0.08
     IMPLEMENT
    -0.07
    teness
    -0.07
    holiday
    -0.07
    瘪
    -0.07
    HEMA
    -0.07
    职业技术
    -0.07
    搋
    -0.07
    杵
    -0.07
    ENTICATION
    -0.07
    POSITIVE LOGITS
     уверен
    0.07
     aura
    0.07
     קטנים
    0.06
     אלינו
    0.06
     privat
    0.06
     indexes
    0.06
     fleet
    0.06
    基金
    0.06
     方
    0.06
    延续
    0.06
    Activations Density 0.002%

    No Known Activations