© 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. 8882
    Prev
    Next
    INDEX
    Explanations

    practice

    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
    .nickname
    -0.08
     بداية
    -0.07
    ienza
    -0.07
     newsletters
    -0.07
    蘸
    -0.07
     temperatures
    -0.07
    JEXEC
    -0.06
    RecyclerView
    -0.06
     quantidade
    -0.06
    Combo
    -0.06
    POSITIVE LOGITS
    ブル
    0.07
    Critical
    0.07
    ザ
    0.07
     rule
    0.07
    큄
    0.07
     unrelated
    0.06
     implanted
    0.06
    륄
    0.06
     signaling
    0.06
    oplan
    0.06
    Activations Density 0.004%

    No Known Activations