© 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. 8201
    Prev
    Next
    INDEX
    Explanations

    Cyberpunk texts

    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
     seus
    -0.09
    >"
↵
    -0.08
     ct
    -0.07
     Lúc
    -0.07
    外
    -0.07
    essoa
    -0.07
    uego
    -0.07
    ichtig
    -0.07
    inha
    -0.07
    abal
    -0.07
    POSITIVE LOGITS
    铪
    0.08
    _transform
    0.08
    主机
    0.08
    _RB
    0.08
     suppress
    0.08
     decoder
    0.07
    强国
    0.07
     MSNBC
    0.07
    -storage
    0.07
     superiority
    0.07
    Activations Density 0.062%

    No Known Activations