© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 6276
    Prev
    Next
    INDEX
    Explanations

    have

    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
     Ча
    -0.07
     dialog
    -0.07
     tell
    -0.07
    INNER
    -0.07
     Investigation
    -0.07
     conducting
    -0.06
     помог
    -0.06
    .Basic
    -0.06
    这种方法
    -0.06
    𝐘
    -0.06
    POSITIVE LOGITS
    獎
    0.08
    bé
    0.08
    枞
    0.08
    Sem
    0.07
    凭
    0.07
     unlawful
    0.07
    lap
    0.06
    ái
    0.06
    Das
    0.06
     excluded
    0.06
    Activations Density 0.027%

    No Known Activations