© 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. 80017
    Prev
    Next
    INDEX
    Explanations

    ?

    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
     permet
    -0.08
     lesson
    -0.07
    shield
    -0.07
    .highlight
    -0.07
    _Tab
    -0.07
    iday
    -0.07
    .services
    -0.07
    (ierr
    -0.07
    tridge
    -0.06
    normalized
    -0.06
    POSITIVE LOGITS
    它是
    0.07
     dobr
    0.07
    숙
    0.06
    ?):
    0.06
    巡回
    0.06
    技法
    0.06
    msp
    0.06
    וס
    0.06
    byter
    0.06
     выб
    0.06
    Activations Density 0.029%

    No Known Activations