© 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. 75485
    Prev
    Next
    INDEX
    Explanations

    the

    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
     Şi
    -0.07
    òn
    -0.07
    ە
    -0.07
    unci
    -0.07
    iết
    -0.07
    泛
    -0.07
    .Simple
    -0.07
    -No
    -0.07
    供需
    -0.07
    -prom
    -0.06
    POSITIVE LOGITS
     inherits
    0.07
    可以从
    0.07
     leading
    0.06
    knife
    0.06
    typescript
    0.06
    _blocks
    0.06
    还要
    0.06
    _Int
    0.06
     SDK
    0.06
     disadvantage
    0.06
    Activations Density 0.005%

    No Known Activations