© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 39953
    Prev
    Next
    INDEX
    Explanations

    =

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     frontline
    -0.07
    زيد
    -0.07
     streak
    -0.06
    燊
    -0.06
    .NoError
    -0.06
    >').
    -0.06
    _phase
    -0.06
     chaining
    -0.06
    迈向
    -0.06
    맜
    -0.06
    POSITIVE LOGITS
    ель
    0.08
    ва
    0.07
     botanical
    0.07
    환경
    0.07
    unden
    0.07
     arena
    0.07
    ;base
    0.07
     subpo
    0.07
     ivory
    0.07
    观光
    0.07
    Activations Density 0.002%

    No Known Activations