© 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. 19-RESID-POST-AA
    11. 5103
    Prev
    Next
    INDEX
    Explanations

    bouncing body parts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ersed
    -0.07
    lard
    -0.07
    Lf
    -0.07
    остей
    -0.07
    ᕑ
    -0.07
     Csv
    -0.06
     excel
    -0.06
     perpendicular
    -0.06
     limiting
    -0.06
     flushed
    -0.06
    POSITIVE LOGITS
    💤
    0.07
     мар
    0.07
    inar
    0.07
    trib
    0.07
    �
    0.07
     timeframe
    0.07
     większość
    0.07
    ランキング
    0.07
    _SIGNAL
    0.07
    ço
    0.07
    Activations Density 0.063%

    No Known Activations