© 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. 11-RESID-POST-AA
    11. 21309
    Prev
    Next
    INDEX
    Explanations

    Fabric of spacetime

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     preferredStyle
    -0.07
    addAction
    -0.07
    .addAction
    -0.06
    혀
    -0.06
    Spy
    -0.06
    Species
    -0.06
    .SwingConstants
    -0.06
     inputStream
    -0.06
    adius
    -0.06
    thest
    -0.06
    POSITIVE LOGITS
    _eff
    0.07
     Market
    0.07
    eterangan
    0.07
     mortar
    0.07
    metrics
    0.07
    -Americans
    0.06
     Đường
    0.06
    _UTIL
    0.06
     Kentucky
    0.06
    _det
    0.06
    Activations Density 0.004%

    No Known Activations