© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 70181
    Prev
    Next
    INDEX
    Explanations

    Titanic disaster

    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
     touchdowns
    -0.07
    画面
    -0.07
    ことができます
    -0.07
     GestureDetector
    -0.07
    complexContent
    -0.07
    ellido
    -0.06
     leth
    -0.06
    当之
    -0.06
    ++++++++++++++++++++++++++++++++
    -0.06
    积极探索
    -0.06
    POSITIVE LOGITS
     Never
    0.08
    ADOW
    0.07
    证券交易
    0.07
    Reduc
    0.07
    Anal
    0.06
    buy
    0.06
    ")));
↵
    0.06
    Indeed
    0.06
    ovie
    0.06
     leasing
    0.06
    Activations Density 0.010%

    No Known Activations