© 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. 8205
    Prev
    Next
    INDEX
    Explanations

    say number

    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
    anger
    -0.07
     elevator
    -0.07
    ecal
    -0.07
    ------↵
    -0.07
     Cognitive
    -0.06
    ﯶ
    -0.06
    أفر
    -0.06
    ONUS
    -0.06
    ОН
    -0.06
    ることは
    -0.06
    POSITIVE LOGITS
     Handling
    0.07
    _act
    0.07
    保税
    0.07
    ropical
    0.07
    -known
    0.07
    resizing
    0.07
    甜蜜
    0.07
     floating
    0.07
    -Le
    0.07
    продаж
    0.06
    Activations Density 0.004%

    No Known Activations