© 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. 15-RESID-POST-AA
    6. 30915
    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
    .context
    -0.07
     зрения
    -0.07
    พบ
    -0.07
     jogador
    -0.07
     stabilize
    -0.07
     rats
    -0.06
    lli
    -0.06
     gehört
    -0.06
    rita
    -0.06
     социально
    -0.06
    POSITIVE LOGITS
    评级
    0.07
     operands
    0.07
    映
    0.07
     {}↵
    0.07
     fChain
    0.07
    Remote
    0.07
    _REPO
    0.07
    	esc
    0.07
     Assy
    0.07
    .Private
    0.07
    Activations Density 0.007%

    No Known Activations